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

    Neuronpedia

    INDEX
    Explanations

    choices and decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puls
    -0.08
     buf
    -0.07
     מג
    -0.07
    媪
    -0.07
    _CONNECTION
    -0.07
    悬念
    -0.07
    _notification
    -0.07
    OptionsMenu
    -0.07
    (message
    -0.06
     mell
    -0.06
    POSITIVE LOGITS
    全国
    0.08
     Anti
    0.08
    otyping
    0.08
    FE
    0.07
    焊接
    0.07
    陆军
    0.07
    𒊑
    0.07
    ")↵↵
    0.07
    ochond
    0.07
    aders
    0.07
    Act Density 0.007%

    No Known Activations