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

    Neuronpedia

    INDEX
    Explanations

    wonder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Occurs
    -0.07
     catcher
    -0.07
    '+
    -0.07
    Sup
    -0.06
    .All
    -0.06
    PK
    -0.06
     keys
    -0.06
     certifications
    -0.06
     キ
    -0.06
    항
    -0.06
    POSITIVE LOGITS
     wondered
    0.08
    监
    0.07
     imagined
    0.07
     wondering
    0.07
     partnering
    0.07
    .sourceforge
    0.07
    .AP
    0.07
     ver
    0.07
    bert
    0.07
    .bed
    0.07
    Act Density 0.006%

    No Known Activations