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

    Neuronpedia

    INDEX
    Explanations

    Bangladesh

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poses
    -0.27
     drowned
    -0.27
     Tucker
    -0.27
    boot
    -0.27
    lösung
    -0.26
     drowning
    -0.25
     circumstance
    -0.25
    _DX
    -0.25
    ç¼£
    -0.24
     reader
    -0.24
    POSITIVE LOGITS
    çĥ¨
    0.29
    gomery
    0.26
    issions
    0.26
    çķĮ
    0.26
     livre
    0.26
     sche
    0.25
    åĩłä¹İæĺ¯
    0.24
    lld
    0.24
    MSG
    0.24
    ев
    0.23
    Act Density 0.006%

    No Known Activations