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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fois
    -0.08
     dri
    -0.07
    erring
    -0.06
     presses
    -0.06
    .social
    -0.06
    ジア
    -0.06
    qn
    -0.06
    instancetype
    -0.06
    _cpu
    -0.06
    °F
    -0.06
    POSITIVE LOGITS
    _OBS
    0.07
    密
    0.06
     Zahl
    0.06
    _EDITOR
    0.06
    수의
    0.06
    Mapping
    0.06
    \Routing
    0.06
    =sys
    0.06
     fighter
    0.06
     kích
    0.06
    Act Density 0.039%

    No Known Activations