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

    Neuronpedia

    INDEX
    Explanations

    baby

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fires
    -0.07
    Ε
    -0.07
    으로
    -0.07
    UE
    -0.07
    My
    -0.07
    NECTION
    -0.07
    ِّ
    -0.06
    ُه
    -0.06
    ่าน
    -0.06
    	cl
    -0.06
    POSITIVE LOGITS
    /Public
    0.06
     Disabilities
    0.06
    /Typography
    0.06
    _OK
    0.06
    StringUtil
    0.06
     tal
    0.06
    sizlik
    0.06
     hemp
    0.06
    _PAYMENT
    0.06
    شة
    0.06
    Act Density 0.008%

    No Known Activations