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

    Neuronpedia

    INDEX
    Explanations

    Walt and VW names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    graph
    0.87
    on
    0.82
    cyte
    0.79
    glas
    0.78
    dL
    0.77
    cyclohex
    0.76
    cracker
    0.76
    calc
    0.75
    gård
    0.73
    cx
    0.73
    POSITIVE LOGITS
    <0x0D>
    0.92
    </b>
    0.83
    は
    0.82
    </strong>
    0.81
    是
    0.81
    는
    0.79
    ↵
    0.77
    }
    0.76
    </code>
    0.74
    ﻢ
    0.73
    Act Density 0.000%

    No Known Activations