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

    Neuronpedia

    INDEX
    Explanations

    a little bit of resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Default
    0.44
     discontinue
    0.44
     mention
    0.43
     default
    0.42
     respons
    0.41
     warranties
    0.41
     rebut
    0.40
     des
    0.40
     di
    0.40
     rhet
    0.39
    POSITIVE LOGITS
     масштаб
    0.55
    INA
    0.49
     공연
    0.48
    場合に
    0.47
    OTH
    0.46
    myY
    0.45
    엠
    0.44
    䨘
    0.44
     INDUSTR
    0.43
    பம்
    0.43
    Act Density 0.002%

    No Known Activations