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

    Neuronpedia

    INDEX
    Explanations

    java.util imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    originals
    0.41
    ListIterator
    0.40
    Atoi
    0.38
    burner
    0.37
    Burn
    0.37
    Red
    0.37
     mdl
    0.36
     hydraulic
    0.36
     romano
    0.36
     بينهم
    0.36
    POSITIVE LOGITS
     unf
    0.40
    olare
    0.37
     merely
    0.37
     \*
    0.35
    мою
    0.35
     differentiates
    0.35
    chop
    0.34
    mehr
    0.33
     interest
    0.33
     penetrates
    0.33
    Act Density 0.000%

    No Known Activations