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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oldem
    -0.07
    recommend
    -0.06
     televis
    -0.06
    iguiente
    -0.06
    teil
    -0.06
    Cors
    -0.06
    コレ
    -0.06
    女孩子
    -0.06
    archivo
    -0.06
    $text
    -0.06
    POSITIVE LOGITS
    .play
    0.07
     Eden
    0.07
    asonry
    0.07
     shelter
    0.07
     proven
    0.07
    _CL
    0.07
    Hay
    0.07
    _TRIANGLE
    0.07
    startswith
    0.07
     WebGL
    0.07
    Act Density 0.750%

    No Known Activations