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

    Neuronpedia

    INDEX
    Explanations

    Code/Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     společně
    -0.07
     pian
    -0.07
     жовтня
    -0.07
    acağız
    -0.06
     Agility
    -0.06
     Ukraj
    -0.06
     disb
    -0.06
    .sess
    -0.06
    .Dir
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    station
    0.06
     damn
    0.06
     employers
    0.06
    膜
    0.06
     loved
    0.06
    인
    0.06
    /***************************************************************************↵
    0.06
    ateway
    0.06
    mono
    0.06
    _pay
    0.06
    Act Density 0.000%

    No Known Activations