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

    Neuronpedia

    INDEX
    Explanations

    code and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marvel
    0.42
     Forbes
    0.41
     তিনটা
    0.40
     Pharmacology
    0.40
     발행
    0.39
     Properties
    0.39
     Holdings
    0.39
     Partners
    0.39
     Childs
    0.39
     检测
    0.38
    POSITIVE LOGITS
    '''
    0.44
    """.
    0.42
    தி
    0.39
    &$\
    0.39
    .'.
    0.39
    .'''
    0.39
    確実に
    0.38
    vila
    0.38
    fromCharCode
    0.38
    between
    0.37
    Act Density 0.000%

    No Known Activations