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

    Neuronpedia

    INDEX
    Explanations

    two cultures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ereal
    0.39
    best
    0.38
    Support
    0.38
    mode
    0.36
    leti
    0.36
     छापे
    0.35
    hind
    0.35
    support
    0.35
     Expert
    0.35
    敤
    0.35
    POSITIVE LOGITS
     remplacement
    0.49
     باع
    0.47
     samoglas
    0.40
     counc
    0.39
    ształ
    0.39
     замены
    0.39
     പറയ
    0.39
     wpływ
    0.39
     ära
    0.38
     परामर्श
    0.38
    Act Density 0.000%

    No Known Activations