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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    services
    -0.07
    Hy
    -0.07
     kd
    -0.06
    Tim
    -0.06
    Manip
    -0.06
    })();
    -0.06
    suppress
    -0.06
     slic
    -0.06
    robot
    -0.06
    Rus
    -0.06
    POSITIVE LOGITS
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
     avait
    0.07
    DB
    0.07
    slideDown
    0.06
    άλι
    0.06
    CNT
    0.06
    ento
    0.06
     πλη
    0.06
     μεγ
    0.06
     …↵
    0.06
    Act Density 0.043%

    No Known Activations