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

    Neuronpedia

    INDEX
    Explanations

    else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Almost
    -0.07
     ''.
    -0.07
     Iceland
    -0.07
    _ok
    -0.06
     Transmit
    -0.06
    าถ
    -0.06
    .po
    -0.06
     cemetery
    -0.06
    Gun
    -0.06
    Relative
    -0.06
    POSITIVE LOGITS
    -taking
    0.07
    periment
    0.06
    ión
    0.06
    /de
    0.06
    ट
    0.06
     banda
    0.06
    試
    0.06
    stin
    0.06
    ocked
    0.06
    ERVED
    0.06
    Act Density 0.016%

    No Known Activations