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

    Neuronpedia

    INDEX
    Explanations

    ` not `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cytosol
    0.52
    walla
    0.49
     treasury
    0.49
    נה
    0.48
     сторона
    0.47
    anez
    0.47
     phosphorylated
    0.47
    robespierre
    0.47
    lisher
    0.47
    㧕
    0.46
    POSITIVE LOGITS
    d
    0.53
    am
    0.45
    ighting
    0.44
    y
    0.43
    F
    0.43
    وم
    0.43
     criterio
    0.42
    Sound
    0.42
    Frequency
    0.42
     enkel
    0.41
    Act Density 0.000%

    No Known Activations