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

    Neuronpedia

    INDEX
    Explanations

    disposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     creams
    -0.07
     صلى
    -0.07
     KT
    -0.07
    Ар
    -0.06
    居民
    -0.06
    Gain
    -0.06
    From
    -0.06
    lei
    -0.06
    unities
    -0.06
    from
    -0.06
    POSITIVE LOGITS
     inserted
    0.07
    ngthen
    0.07
    orne
    0.07
     supplemental
    0.07
     untrue
    0.07
     пунк
    0.06
     adoption
    0.06
     obey
    0.06
     /*----------------------------------------------------------------
    0.06
     Dispose
    0.06
    Act Density 0.012%

    No Known Activations