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

    Neuronpedia

    INDEX
    Explanations

    legal, constitutional texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     convinced
    -0.07
    _suite
    -0.07
    CompatActivity
    -0.07
    Plan
    -0.07
    ured
    -0.07
    .Resources
    -0.06
    TRAIN
    -0.06
     teach
    -0.06
     Coral
    -0.06
     molec
    -0.06
    POSITIVE LOGITS
    锦
    0.07
     �
    0.06
     Appears
    0.06
     theres
    0.06
    COOKIE
    0.06
    kového
    0.06
    ‌م
    0.06
     yeniden
    0.06
    LEAN
    0.06
     }
↵
↵
    0.06
    Act Density 0.006%

    No Known Activations