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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jack
    -0.06
    olib
    -0.06
    	token
    -0.06
     Grow
    -0.06
     trapped
    -0.06
     chast
    -0.06
    Chair
    -0.06
     println
    -0.06
     soared
    -0.06
    hash
    -0.06
    POSITIVE LOGITS
    یمت
    0.07
    ево
    0.07
     GLfloat
    0.07
    _WATER
    0.07
    디시
    0.06
    iddy
    0.06
    ение
    0.06
    нием
    0.06
    Yes
    0.06
    _after
    0.06
    Act Density 0.000%

    No Known Activations