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

    Neuronpedia

    INDEX
    Explanations

    question and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wrangler
    0.73
     丨
    0.72
     Kubrick
    0.71
     stalls
    0.70
     superbly
    0.67
    ]));
    0.66
     estreia
    0.66
    𓇼
    0.66
     raving
    0.64
    จำนวน
    0.64
    POSITIVE LOGITS
    }">
    0.80
     vacuna
    0.79
    м
    0.78
    }->
    0.75
    س
    0.74
    úrg
    0.73
    }",
    0.71
    }"
    0.70
    ы
    0.70
    োর
    0.69
    Act Density 0.001%

    No Known Activations