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

    Neuronpedia

    INDEX
    Explanations

    extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρών
    -0.06
     Ji
    -0.06
    ávka
    -0.06
     developer
    -0.06
     enumerator
    -0.06
    추천
    -0.06
    PX
    -0.06
    circle
    -0.06
     jointly
    -0.06
     yearly
    -0.06
    POSITIVE LOGITS
    .DisplayStyle
    0.07
    addtogroup
    0.07
    arDown
    0.06
    ılıp
    0.06
    .Compose
    0.06
     latex
    0.06
    (UnityEngine
    0.06
     Đặc
    0.06
     masculinity
    0.06
     harness
    0.06
    Act Density 0.006%

    No Known Activations