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

    Neuronpedia

    INDEX
    Explanations

    intended users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coniferous
    0.43
    Secondary
    0.41
     NAVIGATION
    0.38
     wire
    0.38
    ими
    0.38
    عية
    0.36
     rusting
    0.35
     ern
    0.35
    textAlign
    0.35
    配送
    0.35
    POSITIVE LOGITS
    aille
    0.41
     нес
    0.41
    noodles
    0.41
    iteurs
    0.40
    uc
    0.39
    tokens
    0.39
     kaha
    0.39
     नयी
    0.39
     cat
    0.38
     MUM
    0.38
    Act Density 0.000%

    No Known Activations