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

    Neuronpedia

    INDEX
    Explanations

    study resources and practice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invariable
    0.41
     ants
    0.40
     coalescence
    0.39
     CentOS
    0.39
     expeditions
    0.38
     dilat
    0.38
     Silverstone
    0.38
     Debian
    0.37
     nieces
    0.37
     muestras
    0.37
    POSITIVE LOGITS
     Studying
    0.61
     Study
    0.60
    Study
    0.59
     Stud
    0.58
    study
    0.56
    Stud
    0.55
     study
    0.54
    notes
    0.53
     notes
    0.51
     studying
    0.50
    Act Density 0.001%

    No Known Activations