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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prosper
    -0.07
    -select
    -0.07
    Issue
    -0.06
     illustrates
    -0.06
    ıntı
    -0.06
     Assets
    -0.06
     illustrated
    -0.06
     Focus
    -0.06
    XMLElement
    -0.06
     simplest
    -0.06
    POSITIVE LOGITS
    暗
    0.07
    rown
    0.06
    vý
    0.06
     Pam
    0.06
    扩
    0.06
     russ
    0.06
     vin
    0.06
     tir
    0.06
     feather
    0.06
     pods
    0.06
    Act Density 0.026%

    No Known Activations