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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mujeres
    -0.07
    rtl
    -0.07
     şiş
    -0.07
    ascript
    -0.06
     dispute
    -0.06
    itizer
    -0.06
    aque
    -0.06
    quares
    -0.06
    e
    -0.06
    prepared
    -0.06
    POSITIVE LOGITS
    .GetProperty
    0.07
    ắm
    0.07
    _LABEL
    0.07
     澳
    0.06
     Labrador
    0.06
    (from
    0.06
     Anch
    0.06
     tecn
    0.06
     Powers
    0.06
    (coll
    0.06
    Act Density 0.069%

    No Known Activations