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

    Neuronpedia

    INDEX
    Explanations

    abilities and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <
    0.37
     acronym
    0.37
     totaling
    0.35
     chall
    0.35
    ्यालय
    0.35
     trying
    0.34
     dissatisf
    0.34
     storyboard
    0.34
     गेले
    0.33
     review
    0.32
    POSITIVE LOGITS
    能力
    1.46
     ability
    1.35
     kemampuan
    1.35
     способности
    1.34
     capability
    1.33
     capabilities
    1.32
     capacidad
    1.26
     abilities
    1.22
     способность
    1.21
     capacidade
    1.20
    Act Density 0.065%

    No Known Activations