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

    Neuronpedia

    INDEX
    Explanations

    Western culture, wild relatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    track
    0.43
     होप
    0.42
     Armenia
    0.40
    ulaire
    0.40
     presid
    0.40
    Este
    0.39
     Presidency
    0.39
    瑢
    0.39
     സ്ഥാപ
    0.38
     Este
    0.38
    POSITIVE LOGITS
    STARTED
    0.42
    恁
    0.37
     identifications
    0.36
     blushed
    0.36
     constraints
    0.36
    clid
    0.36
     incontr
    0.35
     cones
    0.35
    abst
    0.35
    constraints
    0.34
    Act Density 0.000%

    No Known Activations