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

    Neuronpedia

    INDEX
    Explanations

    catching exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTBase
    0.47
    庥
    0.46
    റിച്ച്
    0.45
     záb
    0.45
    Else
    0.44
    рино
    0.44
    क्षात
    0.43
    CubeSize
    0.43
    Authenticator
    0.43
    Longueur
    0.43
    POSITIVE LOGITS
     In
    0.42
     Trans
    0.39
     moderately
    0.39
     Bypass
    0.39
     F
    0.38
    null
    0.38
     ис
    0.38
     FAQ
    0.38
     bypassed
    0.38
    is
    0.38
    Act Density 0.007%

    No Known Activations