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

    Neuronpedia

    INDEX
    Explanations

    dirty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     omission
    -0.08
     NoSuchElementException
    -0.07
    averse
    -0.07
    etections
    -0.07
     babe
    -0.06
     prevention
    -0.06
    caster
    -0.06
    .ComboBoxStyle
    -0.06
     чуд
    -0.06
     이제
    -0.06
    POSITIVE LOGITS
     dirty
    0.18
     Dirty
    0.15
    Dirty
    0.14
    dirty
    0.13
     filthy
    0.10
     dirt
    0.09
    irty
    0.09
     Dirt
    0.09
    ilty
    0.08
    .dirty
    0.07
    Act Density 0.004%

    No Known Activations