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

    Neuronpedia

    INDEX
    Explanations

    behind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ok
    -0.07
    Hat
    -0.07
    ,val
    -0.07
     mænd
    -0.07
     Resolve
    -0.07
    functional
    -0.07
     Hat
    -0.07
     Oh
    -0.07
     Aw
    -0.06
     Poster
    -0.06
    POSITIVE LOGITS
     bye
    0.07
     donating
    0.06
     neu
    0.06
    (sprite
    0.06
    hero
    0.06
    clone
    0.06
     formul
    0.06
    bio
    0.06
     �
    0.06
     harass
    0.06
    Act Density 0.004%

    No Known Activations