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

    Neuronpedia

    INDEX
    Explanations

    denied or desiring input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    broom
    0.46
    ontrol
    0.41
     главным
    0.39
     Old
    0.39
    mate
    0.38
    Old
    0.37
    ເມ
    0.37
     ಮುಖ್ಯ
    0.37
    IMPORT
    0.37
     হইতেছিল
    0.37
    POSITIVE LOGITS
     পিটার
    0.43
     lược
    0.41
    棌
    0.40
     bezoek
    0.40
     Cupertino
    0.39
    㖅
    0.38
    坚定
    0.38
     निः
    0.37
    鸞
    0.37
     CIR
    0.37
    Act Density 0.000%

    No Known Activations