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

    Neuronpedia

    INDEX
    Explanations

    No

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پخش
    -0.07
    _MATRIX
    -0.07
    .branch
    -0.07
     Rück
    -0.07
     mound
    -0.07
    <char
    -0.06
    Addon
    -0.06
     stos
    -0.06
    opol
    -0.06
     irony
    -0.06
    POSITIVE LOGITS
     yield
    0.07
    enez
    0.07
     Huckabee
    0.07
    no
    0.06
     signaling
    0.06
    -Allow
    0.06
     No
    0.06
    count
    0.06
    ाहरण
    0.06
    agara
    0.06
    Act Density 0.012%

    No Known Activations