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

    Neuronpedia

    INDEX
    Explanations

    filing separately or fecal matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pravi
    0.44
     XI
    0.41
     Xi
    0.39
     અનુસાર
    0.39
     bananas
    0.38
    idot
    0.38
     entries
    0.38
     Pantry
    0.38
    如下
    0.37
     banana
    0.37
    POSITIVE LOGITS
     unbelievably
    0.44
     SAVE
    0.39
    save
    0.39
     save
    0.38
    Save
    0.38
    slate
    0.38
    锉
    0.37
    finden
    0.37
    nydd
    0.37
    ემა
    0.36
    Act Density 0.000%

    No Known Activations