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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arttır
    -0.06
     continents
    -0.06
     klass
    -0.06
    _ACCEPT
    -0.06
     Folder
    -0.05
     Facing
    -0.05
     sectors
    -0.05
     salaries
    -0.05
    ंदर
    -0.05
    -UA
    -0.05
    POSITIVE LOGITS
    esta
    0.07
     provide
    0.07
    寸
    0.07
    %d
    0.07
    Lisa
    0.06
     ACK
    0.06
     #{
    0.06
    _PD
    0.06
    retry
    0.06
     Islamist
    0.06
    Act Density 0.001%

    No Known Activations