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

    Neuronpedia

    INDEX
    Explanations

    conditional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spite
    -0.08
     aviation
    -0.07
     sincerity
    -0.07
    当事
    -0.07
    למו
    -0.07
     erotiske
    -0.07
    _buffer
    -0.07
    😗
    -0.07
     sensitivity
    -0.07
     Dispatcher
    -0.07
    POSITIVE LOGITS
    (embed
    0.07
    0.07
    酆
    0.07
    雇主
    0.07
     Yap
    0.07
     Marco
    0.07
    /cop
    0.07
    熊
    0.07
    ഴ
    0.06
    잃
    0.06
    Act Density 0.005%

    No Known Activations