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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     příč
    -0.07
     accelerate
    -0.07
     winding
    -0.06
     affidavit
    -0.06
     오후
    -0.06
     attorney
    -0.06
    =sub
    -0.06
    _public
    -0.06
    _pub
    -0.06
     والم
    -0.06
    POSITIVE LOGITS
    μφ
    0.07
    cpp
    0.07
    -ignore
    0.06
     العملية
    0.06
    /delete
    0.06
    amaz
    0.06
    uni
    0.06
    elial
    0.06
     lingu
    0.06
    OMPI
    0.06
    Act Density 0.009%

    No Known Activations