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

    Neuronpedia

    INDEX
    Explanations

    heroes and trust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     filenames
    0.54
     summits
    0.52
     estruturas
    0.50
     orbitals
    0.50
     validators
    0.48
     reproductions
    0.48
     แต
    0.48
     files
    0.47
     orbital
    0.47
     sofas
    0.47
    POSITIVE LOGITS
    foaf
    0.46
    eezy
    0.42
    भूत
    0.42
    featured
    0.41
    든
    0.41
    trust
    0.38
     sust
    0.38
     JSTOR
    0.38
     Jazeera
    0.38
    Trust
    0.37
    Act Density 0.022%

    No Known Activations