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

    Neuronpedia

    INDEX
    Explanations

    dates and time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caa
    -0.08
    eczy
    -0.07
    ritional
    -0.07
     FLOAT
    -0.07
    umba
    -0.07
    /');↵
    -0.06
    .Support
    -0.06
     pretending
    -0.06
     Soph
    -0.06
     weigh
    -0.06
    POSITIVE LOGITS
    readcrumb
    0.07
    ♰
    0.06
    POS
    0.06
    Breadcrumb
    0.06
    ﯖ
    0.06
    퍅
    0.06
    ்
    0.06
     peoples
    0.06
    뺐
    0.06
     Change
    0.06
    Act Density 0.049%

    No Known Activations