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

    Neuronpedia

    INDEX
    Explanations

    XML namespaces and schema locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raltar
    0.37
    alassem
    0.37
    ুনিক
    0.36
    ಟನೆ
    0.36
    ierstrass
    0.36
    らず
    0.35
    ッドレス
    0.35
    㤈
    0.35
    ബ്രുവരി
    0.35
    aranth
    0.35
    POSITIVE LOGITS
     raise
    0.33
     bis
    0.32
     xc
    0.32
     filename
    0.31
     processor
    0.31
    X
    0.31
     πλη
    0.31
     pec
    0.31
     levar
    0.31
     and
    0.30
    Act Density 0.000%

    No Known Activations