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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usado
    -0.07
     deutschland
    -0.06
    анд
    -0.06
     lí
    -0.06
     слиз
    -0.06
    _output
    -0.06
     również
    -0.06
    Duration
    -0.06
     svých
    -0.06
     tty
    -0.06
    POSITIVE LOGITS
    .HandleFunc
    0.06
    .proto
    0.06
    .cal
    0.06
    ,…
    0.06
    +'.
    0.06
    vida
    0.06
    Republican
    0.06
    ophil
    0.06
    prepare
    0.06
    IVEN
    0.06
    Act Density 0.019%

    No Known Activations