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

    Neuronpedia

    INDEX
    Explanations

    with a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adding
    0.38
     amount
    0.35
     embodying
    0.34
     taking
    0.33
     realizing
    0.33
     valam
    0.33
     anum
    0.33
     creating
    0.32
     bringing
    0.32
     tratando
    0.32
    POSITIVE LOGITS
     hjälp
    0.57
     origins
    0.55
     unmatched
    0.47
     ajutor
    0.47
     roots
    0.46
     помощью
    0.46
     plenty
    0.46
     unrival
    0.46
    standing
    0.44
     contributions
    0.44
    Act Density 0.020%

    No Known Activations