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

    Neuronpedia

    INDEX
    Explanations

    equations and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.57
     —
    -0.51
     Sub
    -0.51
     ProtoMessage
    -0.50
     mergeFrom
    -0.50
     zu
    -0.49
    accumulate
    -0.49
     Bra
    -0.48
     (_
    -0.47
     _
    -0.47
    POSITIVE LOGITS
     unſ
    0.67
     malin
    0.64
     itſelf
    0.63
     pleaſure
    0.63
    SPJ
    0.61
     Argyle
    0.60
    \{\\
    0.60
     leſs
    0.59
     occaf
    0.59
     uniqlo
    0.59
    Act Density 3.660%

    No Known Activations