Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of measurements and assessments in experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Spatial navigation or mazes

    np_acts-logits-general · gemini-2.0-flash

    finding a way out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.66
    tamol
    -0.62
     einsch
    -0.58
    tvguidetime
    -0.57
     vroeg
    -0.54
     warrants
    -0.54
    DateTimeFormat
    -0.53
     vroe
    -0.52
     ویکی‌پدیا
    -0.51
     vernacular
    -0.51
    POSITIVE LOGITS
     OMITBAD
    0.62
     obstacle
    0.61
     obstacles
    0.59
     maze
    0.58
    StructEnd
    0.54
     obstáculos
    0.53
     препят
    0.53
     stationary
    0.53
    üyada
    0.52
     boxes
    0.52
    Act Density 0.696%

    No Known Activations