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

    Neuronpedia

    INDEX
    Explanations

    version numbers and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    崠
    0.75
    bacteria
    0.65
    invariant
    0.62
    🈶
    0.58
    र्तन
    0.58
    audit
    0.58
     FACS
    0.58
    concepto
    0.57
    pessoas
    0.57
    婍
    0.57
    POSITIVE LOGITS
    하여
    0.84
    ب
    0.66
    Ꮫ
    0.65
    ك
    0.64
    å
    0.63
    니
    0.61
    ﻱ
    0.61
    Ꮄ
    0.61
    ἃ
    0.60
    この
    0.59
    Act Density 0.145%

    No Known Activations