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

    Neuronpedia

    INDEX
    Explanations

    images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FER
    -0.08
    aniel
    -0.07
    UBLE
    -0.07
    ept
    -0.07
    blo
    -0.07
     brow
    -0.06
     됩니다
    -0.06
     desperation
    -0.06
     haired
    -0.06
    ею
    -0.06
    POSITIVE LOGITS
    hawk
    0.06
     Auswahl
    0.06
    (aa
    0.06
     vegan
    0.06
     LCS
    0.06
    IMG
    0.06
     Rodriguez
    0.06
    exterity
    0.06
    entric
    0.06
    leton
    0.06
    Act Density 0.051%

    No Known Activations