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

    Neuronpedia

    INDEX
    Explanations

    weaknesses and original work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veoma
    0.43
     terang
    0.43
     جوړونک
    0.42
     meget
    0.42
    из
    0.42
     Coast
    0.42
    :...
    0.40
    izowane
    0.40
     paljon
    0.40
     bereit
    0.40
    POSITIVE LOGITS
     armies
    0.38
    餒
    0.37
    屾
    0.36
    ય
    0.34
    革命
    0.34
     ancestral
    0.34
     follic
    0.33
     revolution
    0.33
    利益
    0.32
     resultMap
    0.32
    Act Density 0.000%

    No Known Activations