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

    Neuronpedia

    INDEX
    Explanations

    implied

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highways
    -0.07
     cynical
    -0.07
     highway
    -0.07
     MatSnackBar
    -0.07
     Those
    -0.07
    SharedPreferences
    -0.06
    itas
    -0.06
    \modules
    -0.06
    ительные
    -0.06
    すす
    -0.06
    POSITIVE LOGITS
    _steps
    0.07
     Sil
    0.06
    II
    0.06
     effective
    0.06
     terör
    0.06
    TB
    0.06
     Mehmet
    0.06
     δε
    0.06
    (proc
    0.06
    ()'
    0.06
    Act Density 0.001%

    No Known Activations