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

    Neuronpedia

    INDEX
    Explanations

    desires

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    天地
    -0.08
     Fuse
    -0.07
    fonso
    -0.07
     WHO
    -0.07
    โป
    -0.07
    ్ద
    -0.06
     лица
    -0.06
    .º
    -0.06
     fórum
    -0.06
     Formel
    -0.06
    POSITIVE LOGITS
     misguided
    0.14
     tempted
    0.13
     mistakenly
    0.13
     incorrectly
    0.13
     errone
    0.12
     instinct
    0.12
     inadvertently
    0.12
     miscon
    0.11
     inaccur
    0.11
     wrongly
    0.11
    Act Density 0.172%

    No Known Activations