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

    Neuronpedia

    INDEX
    Explanations

    |-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deter
    -0.06
     شار
    -0.06
    .delivery
    -0.06
    ++;↵↵
    -0.06
    ,val
    -0.06
     implode
    -0.06
    няется
    -0.06
    comma
    -0.05
    unic
    -0.05
     INV
    -0.05
    POSITIVE LOGITS
    RESH
    0.08
    -lived
    0.08
     أمريكي
    0.07
    -Token
    0.07
    yle
    0.07
    _certificate
    0.07
    outil
    0.07
    евые
    0.07
    альні
    0.06
    原始
    0.06
    Act Density 0.000%

    No Known Activations