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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kv
    -0.07
    emes
    -0.07
     concession
    -0.07
    荷
    -0.07
    だが
    -0.07
    (rest
    -0.07
    以
    -0.06
    +$
    -0.06
    /M
    -0.06
     以
    -0.06
    POSITIVE LOGITS
    [maxn
    0.07
    .readFileSync
    0.06
     licensed
    0.06
    _staff
    0.06
    ATALOG
    0.06
    Credential
    0.06
    ياه
    0.06
    ágina
    0.06
     황
    0.06
     Irr
    0.05
    Act Density 0.070%

    No Known Activations