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

    Neuronpedia

    INDEX
    Explanations

    references to actions involving caution or safety measures

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

    visiting or exploration

    np_acts-logits-general · gemini-2.0-flash

    visiting or exploring places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.47
     irmão
    -0.44
     ujednoznacz
    -0.42
    oa̍t
    -0.41
    UniformLocation
    -0.40
     argint
    -0.39
    WriteBarrier
    -0.39
    rootNode
    -0.39
    WebVitals
    -0.39
     frère
    -0.38
    POSITIVE LOGITS
     visit
    0.83
     visits
    0.74
     visita
    0.68
     visitation
    0.66
    visit
    0.65
     visiting
    0.65
     visited
    0.63
     VISIT
    0.62
     visite
    0.60
    visits
    0.60
    Act Density 0.429%

    No Known Activations