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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accuse
    -0.07
    én
    -0.07
    exists
    -0.07
     Talk
    -0.07
     Tud
    -0.07
     estimator
    -0.07
    .scene
    -0.07
    .csrf
    -0.06
    亿元
    -0.06
    rollback
    -0.06
    POSITIVE LOGITS
     غذ
    0.06
     ushort
    0.06
    /at
    0.06
     reshape
    0.06
     thro
    0.06
     "↵↵
    0.06
    @hotmail
    0.06
     ""↵
    0.05
    ',['../
    0.05
     LOL
    0.05
    Act Density 0.185%

    No Known Activations