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

    Neuronpedia

    INDEX
    Explanations

    Received

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myths
    -0.07
     hunt
    -0.06
     BP
    -0.06
     Ir
    -0.06
    ighthouse
    -0.06
     ensuing
    -0.06
    action
    -0.06
    담
    -0.06
     ضمن
    -0.06
     Week
    -0.06
    POSITIVE LOGITS
    _banner
    0.07
     アイ
    0.06
    icot
    0.06
    .:.:.:.:.:.:.:.:
    0.06
     شناخته
    0.06
     seamless
    0.06
     项
    0.06
    .”↵↵↵↵
    0.06
    _DEV
    0.06
     incred
    0.06
    Act Density 0.001%

    No Known Activations