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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olvable
    -0.07
    丘
    -0.07
    queueReusable
    -0.06
    aight
    -0.06
    abor
    -0.06
     Snapchat
    -0.06
    abbit
    -0.06
     deltas
    -0.06
    Finish
    -0.06
    Recording
    -0.06
    POSITIVE LOGITS
    (int
    0.08
     =
    0.07
    .size
    0.07
     kosher
    0.07
    ================
    0.06
    =length
    0.06
    388
    0.06
    拥有
    0.06
    =re
    0.06
    _equ
    0.06
    Act Density 0.002%

    No Known Activations