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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    區
    -0.07
     dreadful
    -0.07
    ，当
    -0.07
     ayrıntı
    -0.07
    ��
    -0.06
     fascination
    -0.06
    вести
    -0.06
     increment
    -0.06
     disaster
    -0.06
    drink
    -0.06
    POSITIVE LOGITS
     kolem
    0.06
    <b
    0.06
    .setOn
    0.06
     perpet
    0.06
    affer
    0.06
     Edwin
    0.06
    できない
    0.06
    .menu
    0.06
     gibi
    0.06
    ülük
    0.06
    Act Density 0.007%

    No Known Activations