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

    Neuronpedia

    INDEX
    Explanations

    providing solutions to problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     após
    0.39
    রীণ
    0.37
     blanchâtre
    0.37
     farlo
    0.37
    的其他
    0.37
    ตาม
    0.36
     possano
    0.36
     після
    0.36
     तले
    0.36
    রা
    0.35
    POSITIVE LOGITS
     providing
    0.43
     Provide
    0.42
     നൽക
    0.41
     offering
    0.39
    providing
    0.39
     setTheme
    0.38
     provides
    0.38
     Brings
    0.36
     provide
    0.36
     partly
    0.36
    Act Density 0.038%

    No Known Activations