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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    钳
    -0.07
    ecal
    -0.07
    图纸
    -0.07
     העבודה
    -0.07
     dbl
    -0.07
    stu
    -0.07
    }->
    -0.07
    续航
    -0.07
    طيب
    -0.07
     Giul
    -0.07
    POSITIVE LOGITS
     Optimization
    0.07
     campaign
    0.07
    佞
    0.07
     federation
    0.06
     Rosen
    0.06
     Damen
    0.06
    有价值的
    0.06
    VB
    0.06
    amo
    0.06
    研讨
    0.06
    Act Density 0.000%

    No Known Activations