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

    Neuronpedia

    INDEX
    Explanations

    range and standard deviation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.81
     متعلقه
    -0.80
    __(/*!
    -0.79
    SourceChecksum
    -0.78
    __':
    -0.70
    consulté
    -0.68
    HandlerContext
    -0.66
    rouvez
    -0.64
    पया
    -0.64
    __':
    -0.63
    POSITIVE LOGITS
     purpoſe
    0.61
     ſeveral
    0.52
     cauſe
    0.51
     ſtre
    0.51
     pleaſure
    0.50
     trimester
    0.47
     feveral
    0.47
     themſelves
    0.45
     disease
    0.45
     himſelf
    0.44
    Act Density 0.007%

    No Known Activations