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

    Neuronpedia

    INDEX
    Explanations

    Water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zhou
    -0.07
     grim
    -0.07
     Mojo
    -0.06
     Jinping
    -0.06
     cli
    -0.06
    /cli
    -0.06
     Mej
    -0.06
     иму
    -0.06
    ĩnh
    -0.06
     cyn
    -0.06
    POSITIVE LOGITS
     Water
    0.23
     water
    0.21
    Water
    0.21
    water
    0.19
     WATER
    0.19
    -water
    0.16
    _WATER
    0.14
    _water
    0.14
     waters
    0.13
    .water
    0.12
    Act Density 0.036%

    No Known Activations