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

    Neuronpedia

    INDEX
    Explanations

    increase or grow

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compounding
    0.48
     slander
    0.48
     compound
    0.46
     kaf
    0.46
     salário
    0.45
    తున్నారు
    0.44
     susah
    0.44
    hours
    0.44
     halal
    0.44
    हूं
    0.44
    POSITIVE LOGITS
    Each
    0.60
     over
    0.58
     Each
    0.55
    Over
    0.55
     creates
    0.52
     overtime
    0.52
     evolves
    0.52
     grows
    0.52
    —
    0.52
     progressively
    0.50
    Act Density 0.000%

    No Known Activations