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

    Neuronpedia

    INDEX
    Explanations

    clean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worth
    -0.07
    anus
    -0.07
     tiger
    -0.07
     chol
    -0.07
     rootView
    -0.07
     Tort
    -0.06
    _UNIQUE
    -0.06
     Lens
    -0.06
    Ven
    -0.06
     کو
    -0.06
    POSITIVE LOGITS
    -labelled
    0.06
    .da
    0.06
    Segoe
    0.06
    -push
    0.06
     _,
    0.06
    　
    0.06
     Üniversitesi
    0.06
    まり
    0.06
    شنامه
    0.06
     arcade
    0.06
    Act Density 0.007%

    No Known Activations