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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     personalities
    -0.07
     недели
    -0.07
     QText
    -0.06
    (ChatColor
    -0.06
     чому
    -0.06
    DetailsService
    -0.06
     TCHAR
    -0.06
    ]()
    -0.06
    bbbb
    -0.06
     všechny
    -0.06
    POSITIVE LOGITS
    (Image
    0.07
    ujících
    0.07
    Pressure
    0.07
    Wa
    0.07
     Bj
    0.07
    ristol
    0.07
    loys
    0.06
    zl
    0.06
    Room
    0.06
     DOWN
    0.06
    Act Density 0.000%

    No Known Activations