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

    Neuronpedia

    INDEX
    Explanations

    writer's block

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    だから
    -0.07
    وزی
    -0.07
     مانند
    -0.07
     unseen
    -0.07
    단
    -0.07
    Function
    -0.07
    USTER
    -0.06
     outrage
    -0.06
    .digest
    -0.06
    -process
    -0.06
    POSITIVE LOGITS
    geries
    0.07
     Charity
    0.07
    ,:
    0.06
    \":\"
    0.06
     ramp
    0.06
    -one
    0.06
    ifting
    0.06
    -array
    0.06
     حجم
    0.06
    _GB
    0.06
    Act Density 0.034%

    No Known Activations