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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     earm
    -0.07
     wm
    -0.06
    hints
    -0.06
    άλυ
    -0.06
    ekim
    -0.06
    akh
    -0.06
    Got
    -0.06
    .alpha
    -0.06
    ота
    -0.06
     затем
    -0.06
    POSITIVE LOGITS
    ....↵↵
    0.07
    ="${
    0.06
     삶
    0.06
     створ
    0.06
    ussels
    0.06
    Rotor
    0.06
    'à
    0.06
    )"
    0.06
    vect
    0.06
     України
    0.06
    Act Density 0.001%

    No Known Activations