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

    Neuronpedia

    INDEX
    Explanations

    ---

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANEL
    -0.06
    ARG
    -0.06
     ".
    -0.06
    allis
    -0.06
    oser
    -0.06
     وص
    -0.06
     fetching
    -0.06
    Ster
    -0.06
     sto
    -0.06
    Dest
    -0.06
    POSITIVE LOGITS
     gle
    0.07
    _NONNULL
    0.07
    _zip
    0.07
     aliqu
    0.06
    (profile
    0.06
    _range
    0.06
    quia
    0.06
     condo
    0.06
    Jun
    0.06
     neutron
    0.06
    Act Density 0.004%

    No Known Activations