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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sat
    -0.07
     �
    -0.06
    .AddColumn
    -0.06
    _fre
    -0.06
    HL
    -0.06
    xab
    -0.06
    castle
    -0.06
    expert
    -0.06
     Facility
    -0.06
    Revision
    -0.06
    POSITIVE LOGITS
     :
    0.07
    istické
    0.07
    洗
    0.06
     overcome
    0.06
    mont
    0.06
    :E
    0.06
     науч
    0.06
     FormGroup
    0.06
    森
    0.06
    ($)
    0.06
    Act Density 0.004%

    No Known Activations