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

    Neuronpedia

    INDEX
    Explanations

    quantity or group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numberWith
    0.41
    ными
    0.40
    ræ
    0.38
     रूई
    0.38
    ாப்
    0.38
    설
    0.38
    ставля
    0.37
     Advent
    0.36
     ആദ്യ
    0.36
    ಣೆ
    0.36
    POSITIVE LOGITS
     millions
    0.48
     iedereen
    0.46
     counselors
    0.45
     সবাই
    0.43
     thousands
    0.43
     neurolog
    0.42
     everybody
    0.41
    Bright
    0.41
     everyone
    0.41
     όλ
    0.41
    Act Density 0.000%

    No Known Activations