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

    Neuronpedia

    INDEX
    Explanations

    non-zero or nontrivial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Melissa
    0.48
     किंवा
    0.48
    Dealing
    0.48
    没什么
    0.46
    dealing
    0.46
    or
    0.45
    ur
    0.45
    Identification
    0.42
    Affected
    0.42
    си
    0.42
    POSITIVE LOGITS
     nontrivial
    0.52
     nonzero
    0.51
     interaction
    0.46
     چنانچہ
    0.45
     komponent
    0.45
     scaler
    0.44
    助于
    0.44
     asymmetries
    0.43
     mural
    0.43
     lazy
    0.43
    Act Density 0.012%

    No Known Activations