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

    Neuronpedia

    INDEX
    Explanations

    the followed by specific nouns or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    فى
    0.51
    Tile
    0.40
    નગર
    0.40
    erta
    0.38
    િતા
    0.38
    aduct
    0.38
    occo
    0.38
    ראה
    0.38
     humankind
    0.38
    אי
    0.37
    POSITIVE LOGITS
     putative
    0.49
     postdoc
    0.48
     tumult
    0.47
     heady
    0.46
     heyday
    0.46
     era
    0.45
     crucible
    0.45
     realm
    0.43
     fraught
    0.43
     kinds
    0.43
    Act Density 0.007%

    No Known Activations