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

    Neuronpedia

    INDEX
    Explanations

    job qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cáps
    0.40
     kaps
    0.39
     hice
    0.39
    ColumnKind
    0.37
     savk
    0.37
     kiles
    0.37
     spasms
    0.36
    つまり
    0.35
     destruir
    0.35
    ifikat
    0.35
    POSITIVE LOGITS
     Bachelor
    0.64
     Proven
    0.57
     preferably
    0.55
    Bachelor
    0.55
     demonstrated
    0.54
     Demonstrated
    0.54
    Proven
    0.51
     bachelor
    0.50
     passionate
    0.50
    Excellent
    0.50
    Act Density 0.004%

    No Known Activations