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

    Neuronpedia

    INDEX
    Explanations

    control, crew, confrontation, trip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﱠ
    0.44
    onChange
    0.40
    όν
    0.39
     экран
    0.38
    unable
    0.37
     judi
    0.37
    db
    0.37
    ává
    0.37
    ￩
    0.37
     pohon
    0.36
    POSITIVE LOGITS
     quelconque
    0.41
     Li
    0.40
     alumno
    0.39
     Genealogy
    0.39
     meses
    0.39
     Vue
    0.39
     Mannschaft
    0.38
     genealogy
    0.38
     Mexique
    0.38
     Londres
    0.37
    Act Density 0.000%

    No Known Activations