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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -colored
    -0.07
    σης
    -0.06
    Frame
    -0.06
    ışı
    -0.06
    .samples
    -0.06
    [frame
    -0.06
    래
    -0.06
    /light
    -0.06
    Hex
    -0.06
     jsou
    -0.06
    POSITIVE LOGITS
    326
    0.07
     unreasonable
    0.06
     Simmons
    0.06
    циклопед
    0.06
    ↵    ↵    ↵
    0.06
     luckily
    0.06
     Pé
    0.06
    });↵↵
    0.06
     psychologists
    0.06
     punt
    0.06
    Act Density 0.059%

    No Known Activations