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

    Neuronpedia

    INDEX
    Explanations

    string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barns
    0.48
    塔
    0.47
     જેટ
    0.42
     परस्मैपदी
    0.41
    PosZ
    0.41
    ModelGrid
    0.41
     Josephine
    0.41
     озе
    0.40
    మ్యాచ్
    0.40
    发动机
    0.40
    POSITIVE LOGITS
     string
    0.82
     strings
    0.80
    string
    0.77
     Strings
    0.75
    strings
    0.72
    Strings
    0.72
     Constant
    0.69
     STRING
    0.69
     literal
    0.69
    STRING
    0.66
    Act Density 0.009%

    No Known Activations