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

    Neuronpedia

    INDEX
    Explanations

    measures and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.54
    Ant
    0.47
    Complex
    0.47
    H
    0.47
    M
    0.46
    How
    0.45
    Current
    0.45
    曷
    0.45
    O
    0.44
    C
    0.44
    POSITIVE LOGITS
     Kiy
    0.48
    ർഡ്
    0.48
     കഴ
    0.46
    体积
    0.45
     tedy
    0.43
     människor
    0.42
     auparavant
    0.42
     tumor
    0.41
     reconciliation
    0.41
     metering
    0.41
    Act Density 0.001%

    No Known Activations