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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DIALOG
    -0.07
     ZERO
    -0.06
     Activation
    -0.06
    -olds
    -0.06
    Living
    -0.06
    Decision
    -0.06
    _hits
    -0.06
    .variable
    -0.06
    variant
    -0.06
    perience
    -0.06
    POSITIVE LOGITS
    応
    0.07
    _DDR
    0.06
    CHandle
    0.06
     Cert
    0.06
     Taken
    0.06
     організа
    0.06
    CLUDING
    0.06
     sortOrder
    0.06
    (parcel
    0.06
     typo
    0.06
    Act Density 0.012%

    No Known Activations