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

    Neuronpedia

    INDEX
    Explanations

    BA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treated
    -0.07
     consolidate
    -0.07
    젤
    -0.07
     commitment
    -0.07
    Ret
    -0.07
     ב
    -0.07
     each
    -0.07
    ={"/
    -0.07
     inst
    -0.07
    Init
    -0.07
    POSITIVE LOGITS
     Palin
    0.08
     vidéos
    0.07
     меди
    0.07
    dfa
    0.07
    公关
    0.07
    Asked
    0.07
     Hanson
    0.07
    Funny
    0.07
     Bav
    0.07
     vene
    0.07
    Act Density 0.004%

    No Known Activations