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

    Neuronpedia

    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glover
    -0.07
    ４
    -0.07
    correct
    -0.07
    levance
    -0.06
    bout
    -0.06
    renderer
    -0.06
     Depart
    -0.06
     organis
    -0.06
    OVE
    -0.06
    maint
    -0.06
    POSITIVE LOGITS
    rypto
    0.08
     втор
    0.07
     Finn
    0.06
     внутрен
    0.06
     merchant
    0.06
    /accounts
    0.06
    :UIControlEventTouchUpInside
    0.06
    ↵↵↵↵↵↵↵
    0.06
    _timeline
    0.06
     männer
    0.06
    Act Density 0.012%

    No Known Activations