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

    Neuronpedia

    INDEX
    Explanations

    being assertive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चारियों
    0.40
     Hush
    0.40
    WAYS
    0.39
    萫
    0.39
     Crouch
    0.38
    Easing
    0.38
    apayati
    0.37
     Haller
    0.36
    एचओ
    0.36
    पाला
    0.36
    POSITIVE LOGITS
     utilizza
    0.43
    ginx
    0.42
     leukocyte
    0.42
     znale
    0.42
     nigeria
    0.42
     ongeveer
    0.41
     comis
    0.41
    ≫
    0.41
     malaysia
    0.40
     glacier
    0.40
    Act Density 0.005%

    No Known Activations