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

    Neuronpedia

    INDEX
    Explanations

    references to ranges or continua

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spectrum of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JB
    -0.47
    after
    -0.44
     JB
    -0.40
     Hil
    -0.38
     Rid
    -0.38
     Jog
    -0.38
     Laid
    -0.38
    injured
    -0.38
     précé
    -0.37
    goods
    -0.37
    POSITIVE LOGITS
     Spectrum
    2.11
     spectrum
    2.08
    Spectrum
    2.05
    spectrum
    1.95
     SPECT
    1.32
     espectro
    1.30
    pektrum
    1.21
     spectra
    1.16
     Spek
    1.13
     spectre
    1.06
    Act Density 0.012%

    No Known Activations