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

    Neuronpedia

    INDEX
    Explanations

    meth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warranty
    -0.08
    -out
    -0.07
    peg
    -0.07
     So
    -0.07
     Blue
    -0.07
    湮
    -0.07
    袪
    -0.07
    Blue
    -0.07
    保证
    -0.06
    aturity
    -0.06
    POSITIVE LOGITS
     liberties
    0.07
     /////
    0.07
     Swagger
    0.07
    (iterator
    0.07
     Mattis
    0.07
     skirt
    0.06
     situação
    0.06
    //=
    0.06
     ECS
    0.06
    ⊦
    0.06
    Act Density 0.012%

    No Known Activations