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

    Neuronpedia

    INDEX
    Explanations

    ar's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samod
    0.39
    TARGETTING
    0.38
     einfache
    0.37
     неболь
    0.36
     certa
    0.36
    ATIVE
    0.35
    gever
    0.35
     практи
    0.35
     непосред
    0.35
    ']);
    0.35
    POSITIVE LOGITS
     Around
    0.34
     Num
    0.32
     ومع
    0.31
    k
    0.31
     Pressure
    0.31
       
    0.30
     F
    0.30
     O
    0.30
     P
    0.30
     Info
    0.30
    Act Density 0.103%

    No Known Activations