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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cerc
    -0.07
     dend
    -0.06
    .Class
    -0.06
     localization
    -0.06
     并
    -0.06
     apprentices
    -0.06
     Chern
    -0.06
    StringLength
    -0.06
     Lies
    -0.06
     dependence
    -0.05
    POSITIVE LOGITS
    揮
    0.07
    ilion
    0.07
    acific
    0.07
    -prefix
    0.07
    owner
    0.07
    given
    0.07
    skyt
    0.07
     =>
    0.07
     речі
    0.07
     디자인
    0.07
    Act Density 0.004%

    No Known Activations