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

    Neuronpedia

    INDEX
    Explanations

    rank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prefs
    -0.06
     skulle
    -0.06
    法国
    -0.06
    umhur
    -0.06
     Rp
    -0.06
     altogether
    -0.06
     earlier
    -0.05
    avel
    -0.05
    .EditValue
    -0.05
     miktar
    -0.05
    POSITIVE LOGITS
    Transparent
    0.08
     Suitable
    0.07
    _SECRET
    0.07
     hiểm
    0.06
     Diana
    0.06
     Single
    0.06
     Modeling
    0.06
     conver
    0.06
    -hearted
    0.06
    oc
    0.06
    Act Density 0.006%

    No Known Activations