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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ักด
    -0.08
    veloper
    -0.07
     sidew
    -0.07
    \'
    -0.07
     foi
    -0.07
     Sad
    -0.06
    'ils
    -0.06
     serão
    -0.06
    údo
    -0.06
    /D
    -0.06
    POSITIVE LOGITS
     Riley
    0.08
     Burke
    0.07
     honeymoon
    0.06
     sola
    0.06
     OMG
    0.06
    elder
    0.06
    manufacturer
    0.06
    Pont
    0.06
    fragment
    0.06
    胶
    0.06
    Act Density 0.000%

    No Known Activations