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

    Neuronpedia

    INDEX
    Explanations

    ian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anghai
    -0.07
     perfil
    -0.07
     grayscale
    -0.07
     sexe
    -0.07
    zp
    -0.07
    'est
    -0.06
    amaha
    -0.06
     indir
    -0.06
     calcul
    -0.06
     EFF
    -0.06
    POSITIVE LOGITS
     reassuring
    0.06
    ian
    0.06
     notifying
    0.06
    529
    0.06
    .LOG
    0.06
    통
    0.06
    ционных
    0.06
     यह
    0.06
    ีท
    0.06
     Kia
    0.06
    Act Density 0.000%

    No Known Activations