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

    Neuronpedia

    INDEX
    Explanations

    ceded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handed
    -1.00
     handed
    -0.95
     Mitchell
    -0.94
     Te
    -0.77
     Mit
    -0.76
    sia
    -0.76
     te
    -0.75
    peak
    -0.71
     mit
    -0.70
     peak
    -0.65
    POSITIVE LOGITS
    AndEndTag
    0.66
     Efq
    0.65
    ValueStyle
    0.64
     itſelf
    0.64
     Shakspeare
    0.63
     Houſe
    0.63
     colorés
    0.63
     COE
    0.61
     Monarchy
    0.60
     pleaſure
    0.59
    Act Density 0.570%

    No Known Activations