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

    Neuronpedia

    INDEX
    Explanations

    building components, references, or interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    מק
    0.41
     છ
    0.41
     Perc
    0.39
     Music
    0.39
     Prog
    0.39
    ấ
    0.39
    ॥
    0.39
     along
    0.38
     competes
    0.38
     deserunt
    0.38
    POSITIVE LOGITS
     sostitu
    0.39
    ޢ
    0.38
    interaction
    0.38
     INTERACTIONS
    0.37
    Shr
    0.37
     renverse
    0.37
    ванных
    0.37
    NSDictionary
    0.36
    вете
    0.36
    Kota
    0.36
    Act Density 0.002%

    No Known Activations