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

    Neuronpedia

    INDEX
    Explanations

    feed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woord
    -0.08
     divine
    -0.08
    об
    -0.07
     ----------------------------------------------------------------------------------------------------------------
    -0.07
    dana
    -0.06
    τικα
    -0.06
    kách
    -0.06
    ुक
    -0.06
     моря
    -0.06
     manually
    -0.06
    POSITIVE LOGITS
     ‎
    0.06
     leases
    0.06
    /io
    0.06
     sided
    0.06
    ỗi
    0.06
    副
    0.06
    _HIGH
    0.06
     сказал
    0.06
    _ghost
    0.06
    Entr
    0.06
    Act Density 0.007%

    No Known Activations