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

    Neuronpedia

    INDEX
    Explanations

    http://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.90
    ’
    0.72
    ক
    0.59
     It
    0.55
     è
    0.55
     Nigeria
    0.54
     enzyme
    0.53
     pantalla
    0.52
     écran
    0.52
     dura
    0.52
    POSITIVE LOGITS
    า
    0.63
    ו
    0.59
    soever
    0.56
    orsement
    0.56
    deficient
    0.55
     அடுத்து
    0.54
    𝗮
    0.54
    stellt
    0.54
    侣
    0.54
    received
    0.53
    Act Density 0.000%

    No Known Activations