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

    Neuronpedia

    INDEX
    Explanations

    assure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noises
    -0.08
    âte
    -0.07
    TN
    -0.07
     баз
    -0.07
    芒
    -0.07
     Gran
    -0.07
     méth
    -0.06
    فئ
    -0.06
    .EOF
    -0.06
    trie
    -0.06
    POSITIVE LOGITS
    ياة
    0.07
    发
    0.07
    让学生
    0.07
    appendTo
    0.07
     אח
    0.07
    حة
    0.07
    /as
    0.07
     wearer
    0.07
    الة
    0.06
     assure
    0.06
    Act Density 0.004%

    No Known Activations