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

    Neuronpedia

    INDEX
    Explanations

    code/equations/misc text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Concern
    -0.06
    .allow
    -0.06
     Bowen
    -0.06
    Calibri
    -0.06
    ляем
    -0.06
     reads
    -0.06
     Documents
    -0.06
     reading
    -0.06
     cheated
    -0.06
     بك
    -0.06
    POSITIVE LOGITS
    arduino
    0.07
     �
    0.06
     migraine
    0.06
     공고
    0.06
    "?↵↵
    0.06
     educator
    0.06
    IRQ
    0.06
    _\
    0.06
     výše
    0.06
    CHED
    0.06
    Act Density 0.000%

    No Known Activations