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

    Neuronpedia

    INDEX
    Explanations

    roommates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #from
    -0.07
     тоже
    -0.07
     setShow
    -0.07
     principalColumn
    -0.06
     Bern
    -0.06
    -0.06
    EP
    -0.06
    _CH
    -0.06
     حو
    -0.06
    ゲ
    -0.06
    POSITIVE LOGITS
    caf
    0.07
    PV
    0.07
    cant
    0.07
    SELF
    0.06
    olest
    0.06
    (filter
    0.06
    гл
    0.06
    Ether
    0.06
     your
    0.06
    tas
    0.06
    Act Density 0.024%

    No Known Activations