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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ousy
    -0.06
    genesis
    -0.06
    iffin
    -0.06
    herence
    -0.06
    .SELECT
    -0.06
     �
    -0.06
    _SWAP
    -0.06
    -this
    -0.06
    angl
    -0.06
    achts
    -0.06
    POSITIVE LOGITS
    时
    0.07
    'C
    0.07
    ’S
    0.07
     Persons
    0.06
    查
    0.06
    ;;;
    0.06
     grows
    0.06
    CVE
    0.06
     ir
    0.06
     grow
    0.06
    Act Density 0.006%

    No Known Activations