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

    Neuronpedia

    INDEX
    Explanations

    model fine-tuning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bery
    -0.07
     základě
    -0.06
     levels
    -0.06
    .use
    -0.06
     fucking
    -0.06
    icie
    -0.06
    ี้
    -0.06
     prediction
    -0.06
    images
    -0.06
     Jamaica
    -0.06
    POSITIVE LOGITS
    ัม
    0.07
    ]):
    0.07
     tbsp
    0.06
     pulmonary
    0.06
    ในการ
    0.06
     lcm
    0.06
     blocking
    0.06
     eup
    0.06
    Plus
    0.06
     convict
    0.06
    Act Density 0.040%

    No Known Activations