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

    Neuronpedia

    INDEX
    Explanations

    academic and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いろんな
    0.96
     একটা
    0.95
     pretty
    0.91
     huge
    0.86
     basically
    0.84
     whopping
    0.84
    ちょっと
    0.83
    がたくさん
    0.82
     irgendwie
    0.81
     montón
    0.81
    POSITIVE LOGITS
     wherein
    0.85
     utilizing
    0.75
     herein
    0.75
     necessitating
    0.69
     Utilizing
    0.68
     utilized
    0.67
     utilizes
    0.67
     utilising
    0.67
     commencing
    0.66
     utilize
    0.64
    Act Density 0.280%

    No Known Activations