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

    Neuronpedia

    INDEX
    Explanations

    #:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λλι
    -0.07
    pig
    -0.07
    ยม
    -0.07
    .conf
    -0.07
     UIP
    -0.07
    �
    -0.06
    Dt
    -0.06
     Dix
    -0.06
    สด
    -0.06
     Jord
    -0.06
    POSITIVE LOGITS
    ABILITY
    0.07
     accepts
    0.06
    的问题
    0.06
    (co
    0.06
    kaar
    0.06
    ARS
    0.06
    ایش
    0.06
     diminish
    0.06
     onStart
    0.06
     fraud
    0.05
    Act Density 0.000%

    No Known Activations