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

    Neuronpedia

    INDEX
    Explanations

    Random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وارد
    -0.07
     eapply
    -0.07
     zároveň
    -0.07
    人才
    -0.06
     JWT
    -0.06
    ملة
    -0.06
    输
    -0.06
    监听
    -0.06
     τρο
    -0.06
    ोर
    -0.06
    POSITIVE LOGITS
     parked
    0.06
    isions
    0.06
    -goal
    0.06
    _function
    0.06
     conserve
    0.06
     PG
    0.06
     vc
    0.06
     enhanced
    0.06
    .impl
    0.06
    іг
    0.06
    Act Density 0.000%

    No Known Activations