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

    Neuronpedia

    INDEX
    Explanations

    feature vector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    package
    0.52
    cognitive
    0.46
    F
    0.44
     insistent
    0.43
     scrutiny
    0.43
    ist
    0.42
    dd
    0.42
    τητα
    0.42
    search
    0.42
    gi
    0.42
    POSITIVE LOGITS
     Change
    0.43
     فا
    0.43
    ologous
    0.42
    állítás
    0.41
    üğ
    0.41
    üglich
    0.41
    áticos
    0.40
     ulter
    0.40
    ologías
    0.40
     이에
    0.40
    Act Density 0.000%

    No Known Activations