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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATORS
    -0.07
    فيل
    -0.07
     før
    -0.07
     Во
    -0.07
    	actor
    -0.07
     동
    -0.07
    Email
    -0.06
     אחד
    -0.06
    眷
    -0.06
    圐
    -0.06
    POSITIVE LOGITS
    .nr
    0.08
     consolidated
    0.07
    раст
    0.07
    /************************************************
    0.06
    rent
    0.06
    rai
    0.06
     Programme
    0.06
     Various
    0.06
    urf
    0.06
    堂
    0.06
    Act Density 0.002%

    No Known Activations