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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recognized
    -0.06
     кисл
    -0.06
     안
    -0.06
    �
    -0.06
    APT
    -0.06
     forks
    -0.05
    aşı
    -0.05
    umbs
    -0.05
     sucking
    -0.05
     jeder
    -0.05
    POSITIVE LOGITS
     node
    0.07
     nets
    0.07
     ink
    0.07
    datable
    0.07
    luž
    0.06
    TMP
    0.06
    .KeyChar
    0.06
    /header
    0.06
     OECD
    0.06
     имп
    0.06
    Act Density 0.005%

    No Known Activations