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

    Neuronpedia

    INDEX
    Explanations

    Hold version upwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …</
    0.41
    ँच
    0.40
    ...@
    0.40
    ქვს
    0.36
    вок
    0.35
    गिरी
    0.35
    まり
    0.35
    0.35
    folios
    0.35
    又は
    0.35
    POSITIVE LOGITS
     celu
    0.40
    ArchivePath
    0.38
     temu
    0.38
     im
    0.38
     나타
    0.38
     القب
    0.38
     impedance
    0.38
    additive
    0.36
     Eleventh
    0.36
    ɐ
    0.36
    Act Density 0.000%

    No Known Activations