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

    Neuronpedia

    INDEX
    Explanations

    skills and experience descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vinaig
    0.50
    :
    0.49
     tracers
    0.47
     hallucin
    0.43
     vox
    0.43
     gauze
    0.42
     trigonometric
    0.42
     yad
    0.42
     säga
    0.41
     firewall
    0.41
    POSITIVE LOGITS
     Furthermore
    0.52
     Ayrıca
    0.52
     Awards
    0.50
    学历
    0.50
     Additionally
    0.49
     Moreover
    0.49
     Nielsen
    0.48
     Experience
    0.48
     Außerdem
    0.46
     Inoltre
    0.46
    Act Density 0.025%

    No Known Activations