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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OUT
    -0.07
    _icall
    -0.07
     CONSTRAINT
    -0.07
    (Return
    -0.07
     Counts
    -0.07
    略
    -0.07
    opes
    -0.07
     Manage
    -0.07
    Operator
    -0.06
    ustom
    -0.06
    POSITIVE LOGITS
    187
    0.07
    .params
    0.06
    Civil
    0.06
     ECS
    0.06
    มต
    0.06
    (byte
    0.06
     губер
    0.06
     syslog
    0.06
    cannot
    0.06
     adoles
    0.06
    Act Density 0.011%

    No Known Activations