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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zero
    -0.07
    っても
    -0.07
     Frost
    -0.07
    ança
    -0.06
    itted
    -0.06
    RuleContext
    -0.06
     Liability
    -0.06
     pisc
    -0.06
    (Calendar
    -0.06
     tohoto
    -0.06
    POSITIVE LOGITS
    /red
    0.07
     ….
    0.06
     ск
    0.06
    OVÁ
    0.06
    Scar
    0.06
    bil
    0.06
    _CONTAINER
    0.06
    pcs
    0.06
    ResponseBody
    0.06
     pname
    0.06
    Act Density 0.059%

    No Known Activations