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

    Neuronpedia

    INDEX
    Explanations

    duplicates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ظˆ
    -0.08
    QueryParam
    -0.06
    keeping
    -0.06
     secluded
    -0.06
    paypal
    -0.06
     Utah
    -0.06
     london
    -0.06
    Philadelphia
    -0.06
    末
    -0.06
     workflows
    -0.06
    POSITIVE LOGITS
     Background
    0.07
     Ting
    0.07
     PUSH
    0.07
     Reign
    0.07
     Some
    0.07
    endez
    0.07
     listOf
    0.07
    .routes
    0.06
     fingert
    0.06
     NB
    0.06
    Act Density 0.018%

    No Known Activations