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

    Neuronpedia

    INDEX
    Explanations

    named entities and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㴼
    0.46
    emics
    0.43
    ellations
    0.42
    㝢
    0.42
    ATORS
    0.40
    인트
    0.40
    ridor
    0.40
    pletion
    0.40
     পেট্র
    0.40
     सीपी
    0.40
    POSITIVE LOGITS
     too
    0.45
     freely
    0.38
     βα
    0.38
     Blanco
    0.38
    too
    0.38
    rei
    0.37
    Powered
    0.36
    rho
    0.36
    过多
    0.36
     Liang
    0.35
    Act Density 0.001%

    No Known Activations