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

    Neuronpedia

    INDEX
    Explanations

    guidance, prompting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     said
    -0.07
     eat
    -0.07
    Salt
    -0.06
    -five
    -0.06
    ﾚ
    -0.06
    plement
    -0.06
     Pants
    -0.06
    .IntegerField
    -0.06
     pants
    -0.06
     заболевания
    -0.06
    POSITIVE LOGITS
     remind
    0.07
    CFG
    0.07
    ched
    0.06
    grad
    0.06
     convincing
    0.06
     teach
    0.06
    CHED
    0.06
    queues
    0.06
    _warn
    0.06
    sched
    0.06
    Act Density 0.049%

    No Known Activations