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

    Neuronpedia

    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    أس
    -0.07
    pat
    -0.06
     lon
    -0.06
     Porn
    -0.06
     OMIT
    -0.06
     ={
    -0.06
     Res
    -0.06
    ываем
    -0.06
    .Read
    -0.06
    TemplateName
    -0.06
    POSITIVE LOGITS
     misunderstanding
    0.07
    هرست
    0.07
     embarrassed
    0.07
     inh
    0.07
     عش
    0.07
     bottoms
    0.06
     созд
    0.06
    历史
    0.06
    .must
    0.06
     فعالیت
    0.06
    Act Density 0.000%

    No Known Activations