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

    Neuronpedia

    INDEX
    Explanations

    adverbs of time/possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VISIBLE
    -0.07
    ections
    -0.06
    طار
    -0.06
     neighbor
    -0.06
    odeled
    -0.06
     العلم
    -0.06
     neighbour
    -0.06
    .read
    -0.06
     delegate
    -0.06
    _new
    -0.06
    POSITIVE LOGITS
    _NB
    0.07
     rapp
    0.07
    efully
    0.07
    now
    0.07
    endforeach
    0.07
     Crash
    0.07
    andra
    0.06
     CONNECT
    0.06
    iously
    0.06
     previously
    0.06
    Act Density 0.072%

    No Known Activations