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

    Neuronpedia

    INDEX
    Explanations

    _TEXTURE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     landing
    -0.08
    🐪
    -0.07
    armac
    -0.07
    培
    -0.07
    .jd
    -0.07
     elevator
    -0.07
    𝓈
    -0.07
     escorte
    -0.07
    ubbo
    -0.07
    不仅
    -0.07
    POSITIVE LOGITS
    Identifier
    0.07
     corruption
    0.07
    数目
    0.07
    currentUser
    0.07
     Flow
    0.06
    حام
    0.06
    发力
    0.06
     bey
    0.06
    ไว
    0.06
     Recorder
    0.06
    Act Density 0.001%

    No Known Activations