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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ुल
    -0.07
    ej
    -0.06
    άνει
    -0.06
    LA
    -0.06
     stern
    -0.06
    Solver
    -0.06
     břez
    -0.06
    _ads
    -0.06
     Ment
    -0.06
     ALTER
    -0.06
    POSITIVE LOGITS
    acle
    0.08
     dit
    0.07
     built
    0.06
     Paid
    0.06
     dich
    0.06
     modification
    0.06
     Operational
    0.06
     CONF
    0.06
    _ASSUME
    0.06
     Scre
    0.06
    Act Density 0.015%

    No Known Activations