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

    Neuronpedia

    INDEX
    Explanations

    refers to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    theme
    0.42
     theme
    0.39
     thematic
    0.38
     Theme
    0.37
    لمه
    0.36
    Theme
    0.36
     presupp
    0.36
    لنا
    0.36
    NavigationView
    0.34
     preset
    0.34
    POSITIVE LOGITS
    Refer
    0.48
     Referral
    0.47
     Refer
    0.47
     रेफर
    0.46
     refer
    0.46
     Ref
    0.44
     Vert
    0.44
     Refs
    0.43
     referral
    0.43
     संदर्भ
    0.43
    Act Density 0.002%

    No Known Activations