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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Consultants
    -0.07
     Respir
    -0.07
     Blades
    -0.07
    	DBG
    -0.07
    luetooth
    -0.07
    상을
    -0.06
     Los
    -0.06
     involvement
    -0.06
    (numero
    -0.06
    مش
    -0.06
    POSITIVE LOGITS
     alteration
    0.07
    _LEAVE
    0.07
    uce
    0.07
    .toJSONString
    0.07
    .equal
    0.07
    的情形
    0.07
    _UTF
    0.07
    黼
    0.07
    orama
    0.07
    的特点
    0.06
    Act Density 0.000%

    No Known Activations