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

    Neuronpedia

    INDEX
    Explanations

    scare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ground
    -0.07
     owe
    -0.07
     owes
    -0.07
     actionable
    -0.07
     pleasures
    -0.07
     bill
    -0.06
    현
    -0.06
     autoplay
    -0.06
    ayer
    -0.06
    茂
    -0.06
    POSITIVE LOGITS
     nervous
    0.08
     scares
    0.08
     scared
    0.08
     shootout
    0.07
     nerv
    0.07
    _su
    0.07
     ic
    0.06
     сер
    0.06
     fright
    0.06
     thrilled
    0.06
    Act Density 0.010%

    No Known Activations