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

    Neuronpedia

    INDEX
    Explanations

    lands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alloy
    -0.07
     residues
    -0.07
    -Star
    -0.07
    シー
    -0.06
    待
    -0.06
     outnumber
    -0.06
    .Binary
    -0.06
    Represent
    -0.06
     Alloy
    -0.06
    mutex
    -0.06
    POSITIVE LOGITS
    chin
    0.07
    acious
    0.07
    well
    0.06
    -date
    0.06
     manual
    0.06
     exercise
    0.06
     �
    0.06
     muc
    0.06
     cannabis
    0.06
    urn
    0.06
    Act Density 0.000%

    No Known Activations