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

    Neuronpedia

    INDEX
    Explanations

    legal agreements and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gonflement
    0.59
     curving
    0.58
     complejos
    0.57
     bekommen
    0.54
     végétation
    0.54
     kmeans
    0.53
     perturbations
    0.53
     potente
    0.52
     fireball
    0.52
     músculos
    0.52
    POSITIVE LOGITS
     hereunder
    0.98
     pursuant
    0.83
    Notwithstanding
    0.79
     hereby
    0.77
     Notwithstanding
    0.77
     notwithstanding
    0.71
     (“
    0.69
     shall
    0.68
     expressly
    0.68
     reasonably
    0.67
    Act Density 0.053%

    No Known Activations