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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gridColumn
    -0.07
     breaks
    -0.07
    出入境
    -0.07
     (;;
    -0.07
    	pop
    -0.07
    本金
    -0.07
    (resultado
    -0.07
    .allow
    -0.07
    _buffer
    -0.07
     vertices
    -0.06
    POSITIVE LOGITS
    raj
    0.07
    忱
    0.07
    精油
    0.07
    CompanyName
    0.07
     таких
    0.07
     Female
    0.07
    ⠇
    0.07
    AF
    0.07
     lj
    0.07
    bj
    0.07
    Act Density 0.020%

    No Known Activations