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

    Neuronpedia

    INDEX
    Explanations

    mask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    187
    -0.08
     Hou
    -0.07
     retro
    -0.07
     Friedrich
    -0.07
     Fred
    -0.07
    winter
    -0.07
     dre
    -0.07
    boro
    -0.07
     развити
    -0.07
     Stephen
    -0.07
    POSITIVE LOGITS
     Mask
    0.08
     MASK
    0.08
     masking
    0.07
     masks
    0.07
     мас
    0.07
    Mask
    0.07
    уск
    0.07
    ask
    0.07
     mask
    0.07
    SelfPermission
    0.07
    Act Density 0.009%

    No Known Activations