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

    Neuronpedia

    INDEX
    Explanations

    pursuing degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     éstos
    0.42
     уси
    0.40
     STORM
    0.39
     augmented
    0.38
     smaller
    0.38
     ultimate
    0.37
     타
    0.37
     redundancy
    0.37
     Johns
    0.37
     critical
    0.36
    POSITIVE LOGITS
    oly
    0.43
    চৈতন্য
    0.39
    unteer
    0.39
     फ्रेंच
    0.38
    ঁচু
    0.38
    cott
    0.37
    TN
    0.37
    rauch
    0.37
    vare
    0.37
    simeq
    0.37
    Act Density 0.000%

    No Known Activations