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

    Neuronpedia

    INDEX
    Explanations

    clustering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pagar
    -0.07
    dates
    -0.07
     partie
    -0.07
     cheer
    -0.07
     javascript
    -0.06
    suspend
    -0.06
    Reaction
    -0.06
     Bapt
    -0.06
     Kaz
    -0.06
    rophe
    -0.06
    POSITIVE LOGITS
    _Param
    0.07
     clustering
    0.07
    LC
    0.07
    lüğ
    0.07
    .lst
    0.06
    _FILE
    0.06
     clumsy
    0.06
     mathematical
    0.06
     расстоя
    0.06
     endif
    0.06
    Act Density 0.005%

    No Known Activations