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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     I
    -0.07
     Umb
    -0.07
    /array
    -0.06
    >a
    -0.06
     Barg
    -0.06
    альної
    -0.06
     You
    -0.06
     yo
    -0.06
     aray
    -0.06
    _heat
    -0.06
    POSITIVE LOGITS
     Mediterranean
    0.07
    غل
    0.07
    086
    0.07
    genres
    0.07
     Olivier
    0.07
     PROGMEM
    0.06
    airro
    0.06
    銷
    0.06
     phê
    0.06
    ><?=
    0.06
    Act Density 0.277%

    No Known Activations