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

    Neuronpedia

    INDEX
    Explanations

    shares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    variable
    -0.07
    不含
    -0.07
    ASE
    -0.07
    Coords
    -0.07
    entes
    -0.07
    ев
    -0.07
     Slate
    -0.07
    Leave
    -0.06
    WN
    -0.06
     estimate
    -0.06
    POSITIVE LOGITS
    reveal
    0.07
    推广应用
    0.07
     luggage
    0.07
    _BUFF
    0.07
    下一步
    0.07
     chast
    0.07
     fireworks
    0.07
    增强了
    0.07
    党建
    0.07
    .pub
    0.07
    Act Density 0.080%

    No Known Activations