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

    Neuronpedia

    INDEX
    Explanations

    Long, complex texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayed
    -0.07
    .mem
    -0.07
     Besch
    -0.07
    词
    -0.07
     Lee
    -0.06
     disaster
    -0.06
    folder
    -0.06
    .TEXT
    -0.06
    _APPEND
    -0.06
    Bubble
    -0.06
    POSITIVE LOGITS
     doping
    0.06
    Votre
    0.06
    ]
↵
    0.06
    (grammar
    0.06
    ศจ
    0.06
     peacefully
    0.06
     guiActive
    0.06
    .",
↵
    0.06
    (Of
    0.06
    @(
    0.06
    Act Density 0.183%

    No Known Activations