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

    Neuronpedia

    INDEX
    Explanations

    experiencing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plá
    -0.06
    (blank
    -0.06
     scrap
    -0.06
     Equip
    -0.06
     vyh
    -0.06
     gaat
    -0.06
    <Type
    -0.06
     Hispanics
    -0.06
    ъ
    -0.06
    oblin
    -0.05
    POSITIVE LOGITS
     Features
    0.07
    ظٹ
    0.06
     внутрен
    0.06
     Awakening
    0.06
    ,r
    0.06
    SEND
    0.06
    /App
    0.06
    --
↵
    0.06
     RL
    0.06
    .clean
    0.06
    Act Density 0.000%

    No Known Activations