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

    Neuronpedia

    INDEX
    Explanations

    Taiwanese addresses, Q&A, Virginia Atlantic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anyeol
    -0.76
    swf
    -0.71
    MTL
    -0.71
    addto
    -0.71
     angef
    -0.69
    orters
    -0.69
    appendix
    -0.69
    axle
    -0.68
    letto
    -0.68
    galvan
    -0.68
    POSITIVE LOGITS
    strup
    0.74
     brig
    0.73
     Toma
    0.72
    TimeUnit
    0.69
     voltmeter
    0.69
    promis
    0.69
    brenner
    0.66
    товая
    0.66
     Schweiz
    0.65
     Chatham
    0.64
    Act Density 0.019%

    No Known Activations