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

    Neuronpedia

    INDEX
    Explanations

    priority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yarat
    -0.07
     stable
    -0.07
    _o
    -0.06
     evenings
    -0.06
    áu
    -0.06
     spherical
    -0.06
    _UT
    -0.06
     그래
    -0.06
     brewed
    -0.06
    _principal
    -0.06
    POSITIVE LOGITS
     -=
    0.06
     earns
    0.06
     #%
    0.06
    -program
    0.06
    %).
    0.06
     الشم
    0.06
     glyphicon
    0.06
    ávis
    0.06
    äm
    0.06
    vincia
    0.06
    Act Density 0.018%

    No Known Activations