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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ihtiy
    -0.07
    วไป
    -0.06
    onomies
    -0.06
    dra
    -0.06
    ncias
    -0.06
     خوبی
    -0.06
    airro
    -0.06
     kịp
    -0.06
     testcase
    -0.06
     Gover
    -0.06
    POSITIVE LOGITS
    ]}</
    0.07
    "},"
    0.06
     Differential
    0.06
     assassination
    0.06
    "If
    0.06
     cuff
    0.06
    ＿＿＿＿
    0.06
    icemail
    0.06
     Till
    0.06
     бесп
    0.06
    Act Density 0.004%

    No Known Activations