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

    Neuronpedia

    INDEX
    Explanations

    code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฬ
    -0.07
     Submit
    -0.06
    Explicit
    -0.06
     غربی
    -0.06
    าคม
    -0.06
     smoked
    -0.06
     населения
    -0.06
     �
    -0.06
    そう
    -0.06
     варт
    -0.06
    POSITIVE LOGITS
    (photo
    0.07
    ass
    0.07
     MER
    0.07
    -step
    0.06
    rox
    0.06
     reve
    0.06
    inn
    0.06
    _save
    0.06
    ASS
    0.06
    PopMatrix
    0.06
    Act Density 0.031%

    No Known Activations