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

    Neuronpedia

    INDEX
    Explanations

    names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nexus
    0.46
     overwhelm
    0.44
     적
    0.44
     gl
    0.43
     reasoning
    0.42
     ipsum
    0.42
     Roboto
    0.41
     *
    0.41
     bits
    0.40
     eslint
    0.39
    POSITIVE LOGITS
    ita
    0.78
    ina
    0.76
    ie
    0.75
    berto
    0.74
    elipe
    0.74
    inda
    0.71
    <unused683>
    0.71
    ika
    0.69
    ena
    0.69
    omir
    0.69
    Act Density 0.056%

    No Known Activations