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

    Neuronpedia

    INDEX
    Explanations

    SQL code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    גידול
    -0.07
     angl
    -0.07
    instancetype
    -0.07
    娱乐平台
    -0.07
    筹码
    -0.07
    _Anim
    -0.06
    nb
    -0.06
    口感
    -0.06
     soils
    -0.06
     blends
    -0.06
    POSITIVE LOGITS
    上传
    0.07
    🛎
    0.07
    恶
    0.07
    trajectory
    0.07
    (Client
    0.07
    對
    0.07
    Ta
    0.07
     This
    0.07
    Mult
    0.06
    eli
    0.06
    Act Density 0.008%

    No Known Activations