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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .match
    -0.07
    BIND
    -0.07
     neboť
    -0.07
     Wash
    -0.06
    KeySpec
    -0.06
     Tears
    -0.06
    -save
    -0.06
    611
    -0.06
    @↵↵
    -0.06
    _home
    -0.06
    POSITIVE LOGITS
    čních
    0.07
     yazar
    0.07
    čná
    0.06
     finan
    0.06
    udded
    0.06
     Gö
    0.06
    สน
    0.06
    ardo
    0.06
     contentious
    0.06
     TableName
    0.06
    Act Density 0.012%

    No Known Activations