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

    Neuronpedia

    INDEX
    Explanations

    descriptions and recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nová
    -0.07
     děti
    -0.07
    _slots
    -0.07
    ultimo
    -0.07
     नर
    -0.07
    las
    -0.07
    .help
    -0.07
     массив
    -0.07
     pomoci
    -0.07
    čel
    -0.06
    POSITIVE LOGITS
    ////////
    0.07
     nonlinear
    0.06
    827
    0.06
    abolic
    0.06
     新
    0.06
     unserer
    0.06
    改
    0.06
     Lif
    0.06
    양
    0.06
    PTION
    0.06
    Act Density 0.001%

    No Known Activations