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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harms
    -0.07
    .ContentType
    -0.07
    ائل
    -0.06
    _assets
    -0.06
    Params
    -0.06
    那里
    -0.06
    Credential
    -0.06
     برای
    -0.06
     progressBar
    -0.06
     dear
    -0.06
    POSITIVE LOGITS
     ㅇㅇ
    0.07
    owie
    0.06
    uppies
    0.06
    xxxxxxxx
    0.06
    jsx
    0.06
    avelength
    0.06
    Trad
    0.06
    uvre
    0.06
     pře
    0.06
     výzkum
    0.06
    Act Density 0.002%

    No Known Activations