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

    Neuronpedia

    INDEX
    Explanations

    resume sections and professional details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    requenz
    0.42
     منهم
    0.41
     ശക്ത
    0.41
     elementów
    0.39
     sinusoid
    0.39
     точек
    0.39
     целом
    0.39
     घना
    0.39
     វា
    0.39
     mujeres
    0.38
    POSITIVE LOGITS
     memberships
    0.55
     certifications
    0.54
     listing
    0.49
     hobbies
    0.45
     EditorGUILayout
    0.45
     Miscellaneous
    0.45
     Bullet
    0.45
     Tertiary
    0.45
    信仰
    0.44
     unless
    0.44
    Act Density 0.042%

    No Known Activations