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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yok
    -0.08
     Obs
    -0.07
    Created
    -0.06
    cak
    -0.06
     Incre
    -0.06
     Biom
    -0.06
    [List
    -0.06
    _avail
    -0.06
     KM
    -0.06
     구
    -0.06
    POSITIVE LOGITS
     eylem
    0.07
    strukce
    0.07
    (em
    0.06
     via
    0.06
     RuntimeError
    0.06
    ěl
    0.06
    _through
    0.06
     grants
    0.06
     })
↵
    0.06
    مة
    0.06
    Act Density 0.004%

    No Known Activations