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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timestamps
    -0.07
     showError
    -0.07
     ridic
    -0.06
    #================================================================
    -0.06
    .isLoading
    -0.06
     Stefan
    -0.06
    sus
    -0.06
    [slot
    -0.06
     어려
    -0.06
    蛛
    -0.06
    POSITIVE LOGITS
     ~
    0.07
     learning
    0.06
     Parcel
    0.06
     icon
    0.06
           ↵
    0.06
     rewarded
    0.06
     calend
    0.06
    ocaust
    0.06
     ->↵
    0.06
     muted
    0.06
    Act Density 0.002%

    No Known Activations