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

    Neuronpedia

    INDEX
    Explanations

    AI Pro, Storage and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     القمر
    0.42
     Chairperson
    0.41
     जहा
    0.39
    desa
    0.38
     Protocols
    0.38
     자체
    0.37
    Vanessa
    0.37
     Always
    0.36
    ework
    0.36
     পরম
    0.36
    POSITIVE LOGITS
    Xt
    0.40
    acod
    0.38
     Laid
    0.38
     அதிகரிக்கும்
    0.38
     beliebt
    0.37
    τρι
    0.37
     laid
    0.35
     النمو
    0.35
    هلاك
    0.35
    饕
    0.35
    Act Density 0.000%

    No Known Activations