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

    Neuronpedia

    INDEX
    Explanations

    equivalent to one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Questo
    -1.11
    不得不说
    -1.00
    ctuary
    -1.00
    psack
    -0.96
    Preparazione
    -0.94
    ViewInit
    -0.93
    zkę
    -0.93
    をご覧
    -0.92
    Which
    -0.91
     nuevas
    -0.91
    POSITIVE LOGITS
     mineures
    0.96
     graciosas
    0.91
     muñecas
    0.90
    értel
    0.88
     mounds
    0.86
    밟
    0.86
     staffel
    0.85
     klokken
    0.85
    ̀i
    0.83
     when
    0.82
    Act Density 0.115%

    No Known Activations