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

    Neuronpedia

    INDEX
    Explanations

    mem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     следует
    -0.07
    titulo
    -0.07
     prostor
    -0.07
     ques
    -0.06
     obchod
    -0.06
     nejsou
    -0.06
     sociology
    -0.06
    heten
    -0.06
     WRITE
    -0.06
    esti
    -0.06
    POSITIVE LOGITS
     buen
    0.06
    仍
    0.06
    _tr
    0.06
    .Live
    0.06
     rootReducer
    0.06
    [strlen
    0.06
    .functions
    0.06
     passes
    0.06
     rec
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations