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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ู
    -0.07
    าด
    -0.07
    ائق
    -0.06
    ê
    -0.06
     cela
    -0.06
    riet
    -0.06
    .Comp
    -0.06
     afr
    -0.06
    　　 　
    -0.05
     prin
    -0.05
    POSITIVE LOGITS
     inhal
    0.06
     الجام
    0.06
    .arrow
    0.06
     corporations
    0.06
    dik
    0.06
     fant
    0.06
     Stud
    0.06
    apeutic
    0.06
    	ex
    0.06
     HOR
    0.06
    Act Density 0.359%

    No Known Activations