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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating problems or errors in coding or technology

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

    I describe my problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    habitation
    -0.38
    Lloyd
    -0.37
    minton
    -0.37
     top
    -0.37
     Lloyd
    -0.35
     inplace
    -0.34
    top
    -0.34
    istic
    -0.33
    atification
    -0.33
    growth
    -0.32
    POSITIVE LOGITS
    featureID
    0.67
    хьтан
    0.53
     malfunction
    0.51
    msgTypes
    0.51
    RenderAtEndOf
    0.50
    ParallelGroup
    0.49
    ThroughAttribute
    0.48
     malfunctions
    0.48
     propOrder
    0.48
     références
    0.47
    Act Density 0.180%

    No Known Activations