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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -my
    -0.07
     moms
    -0.07
     Bachelor
    -0.07
     software
    -0.07
    _anim
    -0.07
    Xi
    -0.07
    -fly
    -0.07
     couldn
    -0.06
    -print
    -0.06
     genus
    -0.06
    POSITIVE LOGITS
     감
    0.06
    zent
    0.06
     порів
    0.06
     Starts
    0.06
     started
    0.06
     оказ
    0.06
     нак
    0.06
    uyển
    0.06
    starts
    0.06
     пов
    0.06
    Act Density 0.020%

    No Known Activations