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

    Neuronpedia

    INDEX
    Explanations

    impossible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erved
    -0.07
     politely
    -0.07
     Yönetim
    -0.07
    _SPEC
    -0.07
     summar
    -0.06
     describing
    -0.06
    .day
    -0.06
     viewHolder
    -0.06
     flexGrow
    -0.06
    _Page
    -0.06
    POSITIVE LOGITS
     impossible
    0.11
     Impossible
    0.08
    Impossible
    0.08
    _|
    0.06
    otta
    0.06
    rowad
    0.06
    possibly
    0.06
     Robinson
    0.06
     Sasha
    0.06
    -Am
    0.06
    Act Density 0.011%

    No Known Activations