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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    从
    -0.07
    _than
    -0.06
    _expr
    -0.06
    .be
    -0.06
    [to
    -0.06
     weekend
    -0.06
     star
    -0.06
    .Enter
    -0.06
    -em
    -0.06
     year
    -0.06
    POSITIVE LOGITS
     asn
    0.07
    uctive
    0.06
    exion
    0.06
    _UNS
    0.06
     ruthless
    0.06
    rophy
    0.06
    史
    0.06
    ction
    0.06
    ambi
    0.06
     Creation
    0.06
    Act Density 0.040%

    No Known Activations