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

    Neuronpedia

    INDEX
    Explanations

    scientific/physics papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VT
    -0.07
    incre
    -0.07
     disparities
    -0.06
     dependence
    -0.06
    Att
    -0.06
    serde
    -0.06
    �
    -0.06
    _simulation
    -0.06
    ']='
    -0.06
    /x
    -0.06
    POSITIVE LOGITS
    EINVAL
    0.07
     düzenli
    0.07
    (:,:,
    0.06
    교회
    0.06
     �
    0.06
     mosque
    0.06
     FRA
    0.06
     Autodesk
    0.06
     TreeSet
    0.06
     پایین
    0.06
    Act Density 0.008%

    No Known Activations