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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     billion
    -0.07
     melanch
    -0.06
     blurred
    -0.06
    Remark
    -0.06
    .contains
    -0.06
     iphone
    -0.06
     GOOD
    -0.06
     unveiled
    -0.06
     ENG
    -0.06
     rem
    -0.06
    POSITIVE LOGITS
    εια
    0.07
    lac
    0.06
    _cli
    0.06
    elu
    0.06
    _mB
    0.06
    े-
    0.06
     पढ़
    0.06
    _accepted
    0.06
    ней
    0.06
     jde
    0.06
    Act Density 0.003%

    No Known Activations