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

    Neuronpedia

    INDEX
    Explanations

    at/the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibrate
    -0.08
    альна
    -0.07
     strstr
    -0.07
     recherche
    -0.06
    !("{}",
    -0.06
    Stick
    -0.06
     chip
    -0.06
    зя
    -0.06
    уч
    -0.06
     правда
    -0.06
    POSITIVE LOGITS
     entertainment
    0.07
     misleading
    0.07
     slun
    0.07
    "No
    0.07
     decorating
    0.06
    .Lock
    0.06
    Will
    0.06
     Secret
    0.06
     Dark
    0.06
    .Dark
    0.06
    Act Density 0.007%

    No Known Activations