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

    Neuronpedia

    INDEX
    Explanations

    experimental setups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaned
    -0.07
    /color
    -0.07
    _PHASE
    -0.07
    лива
    -0.06
    mobile
    -0.06
     lava
    -0.06
    ergarten
    -0.06
    (Global
    -0.06
     starvation
    -0.06
     cider
    -0.06
    POSITIVE LOGITS
    >_
    0.07
    onomies
    0.07
    _StaticFields
    0.06
    ))/(
    0.06
    άρ
    0.06
     mädchen
    0.06
     треб
    0.06
     jeu
    0.06
     ways
    0.06
    :right
    0.06
    Act Density 0.060%

    No Known Activations