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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahaha
    -0.08
     Modi
    -0.07
    ้าต
    -0.07
     Lars
    -0.06
    laughter
    -0.06
     kaldır
    -0.06
     certain
    -0.06
    Int
    -0.06
     περισσότε
    -0.06
     Florian
    -0.06
    POSITIVE LOGITS
    .createStatement
    0.06
     hurl
    0.06
    tax
    0.06
    (lista
    0.06
     flowed
    0.06
    dum
    0.06
     Muss
    0.06
     botanical
    0.06
    _enabled
    0.06
                            ↵
    0.06
    Act Density 0.003%

    No Known Activations