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
     nausea
    -0.10
     retaliation
    -0.08
     watched
    -0.08
     nause
    -0.08
     watching
    -0.08
     inim
    -0.07
     Norris
    -0.07
    _IMPORT
    -0.07
    ஞ
    -0.07
    mern
    -0.07
    POSITIVE LOGITS
    百分
    0.10
     ശതമ
    0.09
    还有
    0.09
     শতাংশ
    0.08
     còn
    0.08
    .attach
    0.08
     വീണ്ടും
    0.08
     percentage
    0.08
     റിപ്പ
    0.08
     (.
    0.08
    Act Density 0.004%

    No Known Activations