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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ປ
    -0.07
     replied
    -0.07
     тому
    -0.07
    乘车
    -0.07
    키
    -0.07
    IU
    -0.07
    _PB
    -0.07
                      ↵
    -0.07
    淖
    -0.07
    TintColor
    -0.07
    POSITIVE LOGITS
     frustrating
    0.07
    ème
    0.07
    ensions
    0.07
     West
    0.07
     doesnt
    0.07
     trimest
    0.07
     complement
    0.06
    믕
    0.06
     BET
    0.06
    grily
    0.06
    Act Density 0.008%

    No Known Activations