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

    Neuronpedia

    INDEX
    Explanations

    Mont

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EM
    -0.07
    em
    -0.07
    ilih
    -0.06
     �
    -0.06
     depois
    -0.06
    istro
    -0.06
    .backup
    -0.06
    inherit
    -0.06
    ício
    -0.06
     Fiction
    -0.06
    POSITIVE LOGITS
    點
    0.08
    _ps
    0.07
    Minimal
    0.07
     Port
    0.07
    .Monad
    0.07
    率
    0.07
     POT
    0.07
    먹
    0.07
    areth
    0.06
    .toInt
    0.06
    Act Density 0.004%

    No Known Activations