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

    Neuronpedia

    INDEX
    Explanations

    expansion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xyz
    -0.08
    aneous
    -0.07
    不堪
    -0.07
     número
    -0.07
    ấm
    -0.07
     türlü
    -0.07
    athom
    -0.07
     shootout
    -0.06
    unden
    -0.06
    𝆳
    -0.06
    POSITIVE LOGITS
    .Template
    0.07
    .ptr
    0.07
    ainers
    0.07
     เป
    0.07
    .single
    0.07
    .dk
    0.07
    AsyncResult
    0.07
     Martial
    0.07
    才行
    0.07
     답변
    0.07
    Act Density 0.007%

    No Known Activations