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

    Neuronpedia

    INDEX
    Explanations

    Foreign language/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﴿
    -0.07
    换句话
    -0.07
    seg
    -0.07
    trer
    -0.07
    \r
    -0.07
    これが
    -0.07
    -0.07
    	side
    -0.07
     ><
    -0.07
    ilor
    -0.07
    POSITIVE LOGITS
    헨
    0.08
     Couch
    0.08
    posable
    0.07
    Pokemon
    0.07
    勤奋
    0.07
     нет
    0.07
    Operator
    0.07
    켓
    0.06
    .onClick
    0.06
     nied
    0.06
    Act Density 0.000%

    No Known Activations