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

    Neuronpedia

    INDEX
    Explanations

    197

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equation
    -0.08
    el
    -0.07
     ctor
    -0.07
    ель
    -0.07
     gear
    -0.06
    flow
    -0.06
    μένα
    -0.06
     pict
    -0.06
     seaw
    -0.06
    Phi
    -0.06
    POSITIVE LOGITS
    漂
    0.07
    ��
    0.07
     ()
↵
    0.06
    _episodes
    0.06
     둘
    0.06
    .cgi
    0.06
     blij
    0.06
     كور
    0.06
     浙江
    0.06
    科学
    0.06
    Act Density 0.008%

    No Known Activations