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

    Neuronpedia

    INDEX
    Explanations

    aha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    亮
    -0.07
     blah
    -0.07
     füh
    -0.07
    듐
    -0.07
    蕙
    -0.07
     Grimm
    -0.07
     attractiveness
    -0.07
     NSW
    -0.07
    養
    -0.07
    quee
    -0.07
    POSITIVE LOGITS
    _foreign
    0.08
     recurse
    0.07
     toReturn
    0.07
     CONTROL
    0.07
     "__
    0.07
    .Max
    0.07
    ran
    0.07
     Kul
    0.07
     Michel
    0.07
    이라고
    0.07
    Act Density 0.006%

    No Known Activations