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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    special character ^{

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     —
    -0.63
     _
    -0.53
    ^
    -0.51
    —
    -0.50
     das
    -0.49
    ^^
    -0.49
     -
    -0.49
     all
    -0.47
     ^
    -0.47
     T
    -0.47
    POSITIVE LOGITS
     pleaſure
    0.98
     Shakspeare
    0.89
     itſelf
    0.88
     diſt
    0.85
     raiſ
    0.84
     becauſe
    0.84
     ſeveral
    0.84
     fathoms
    0.83
     unſ
    0.83
    MemoryWarning
    0.82
    Act Density 3.530%

    No Known Activations