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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    about
    -0.08
    われる
    -0.07
    ta
    -0.07
    IELDS
    -0.06
     Matters
    -0.06
     About
    -0.06
     Together
    -0.06
     </>↵
    -0.06
    grown
    -0.06
    оваться
    -0.06
    POSITIVE LOGITS
     návr
    0.07
     nå
    0.07
    �
    0.06
    (base
    0.06
    ฝ
    0.06
    .Observer
    0.06
     κύ
    0.06
     форме
    0.06
    ,(
    0.06
     αποτε
    0.06
    Act Density 0.076%

    No Known Activations