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

    Neuronpedia

    INDEX
    Explanations

    filtration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cluster
    -0.07
    ゞ
    -0.07
     stunt
    -0.07
    222
    -0.07
     pus
    -0.07
     zero
    -0.06
    INK
    -0.06
     thử
    -0.06
     nowhere
    -0.06
     '--
    -0.06
    POSITIVE LOGITS
     filtration
    0.08
    Ｔ
    0.07
     Funding
    0.07
    χν
    0.07
    .vol
    0.06
    '%(
    0.06
    (QtCore
    0.06
     searchText
    0.06
    ikat
    0.06
    tridges
    0.06
    Act Density 0.004%

    No Known Activations