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

    Neuronpedia

    INDEX
    Explanations

    waiting for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    1.02
    >
    1.01
     in
    0.98
    ization
    0.95
    \
    0.91
    ación
    0.91
    <0x82>
    0.90
    ется
    0.90
    uição
    0.88
     табле
    0.88
    POSITIVE LOGITS
    ES
    1.72
     đợi
    1.33
    AK
    1.31
    AY
    1.30
    IA
    1.27
    AR
    1.26
    LE
    1.26
    X
    1.23
    ST
    1.19
    EN
    1.16
    Act Density 0.057%

    No Known Activations