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

    Neuronpedia

    INDEX
    Explanations

    lips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimizing
    -0.07
     Strategy
    -0.07
    orf
    -0.06
     towers
    -0.06
     Motors
    -0.06
     blij
    -0.06
    iswa
    -0.06
    ”↵↵
    -0.06
     spills
    -0.06
     дли
    -0.06
    POSITIVE LOGITS
    <Integer
    0.07
    (hObject
    0.06
    στο
    0.06
    .opens
    0.06
     istiyor
    0.06
     สำ
    0.06
     Galactic
    0.06
     downright
    0.06
     somew
    0.06
    etest
    0.06
    Act Density 0.063%

    No Known Activations