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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Client
    -0.07
    총
    -0.07
    semb
    -0.06
     Hao
    -0.06
     TEntity
    -0.06
    .ol
    -0.06
    Mirror
    -0.06
    (fullfile
    -0.06
     Hàn
    -0.06
    _WRAPPER
    -0.06
    POSITIVE LOGITS
    φων
    0.07
     Salah
    0.07
    때
    0.06
    -progress
    0.06
     electromagnetic
    0.06
     desperate
    0.06
    music
    0.06
    ゆ
    0.06
     Newsletter
    0.06
     loginUser
    0.06
    Act Density 0.003%

    No Known Activations