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

    Neuronpedia

    INDEX
    Explanations

    company policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sprung
    -0.08
     durchschnitt
    -0.08
     avg
    -0.08
     iso
    -0.08
     평균
    -0.08
     thing
    -0.08
    .avg
    -0.08
     throne
    -0.08
     tiring
    -0.08
     Squ
    -0.07
    POSITIVE LOGITS
     ಸಿಬ್ಬಂದ
    0.12
     personeel
    0.12
     कर्मचार
    0.12
     medewerkers
    0.12
     employees
    0.11
    スタッフ
    0.11
    干部
    0.11
     staff
    0.11
    工作人员
    0.10
     сотрудников
    0.10
    Act Density 0.039%

    No Known Activations