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

    Neuronpedia

    INDEX
    Explanations

    E

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     safe
    -0.06
    eating
    -0.06
     calculate
    -0.06
    Mining
    -0.06
    '];?></
    -0.06
    Feature
    -0.06
     blanket
    -0.06
     idiots
    -0.06
    ecial
    -0.06
     adjunct
    -0.06
    POSITIVE LOGITS
     watchdog
    0.08
    mıştı
    0.07
    apsed
    0.07
    deployment
    0.06
    LOB
    0.06
    .Identity
    0.06
     Yas
    0.06
     submitting
    0.06
    electric
    0.06
    efore
    0.06
    Act Density 0.002%

    No Known Activations