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

    Neuronpedia

    INDEX
    Explanations

    reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♫
    -0.07
     acum
    -0.07
    哪怕是
    -0.07
    ינם
    -0.07
     shortcuts
    -0.07
    告訴
    -0.07
     irr
    -0.07
    �
    -0.07
     thugs
    -0.06
    既可以
    -0.06
    POSITIVE LOGITS
    בת
    0.07
     начала
    0.07
     Provider
    0.07
     SCRIPT
    0.07
    ЛА
    0.07
    opa
    0.07
     правитель
    0.07
     Overlay
    0.07
    Ol
    0.07
     WebSocket
    0.06
    Act Density 0.008%

    No Known Activations