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

    Neuronpedia

    INDEX
    Explanations

    Case

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shemale
    -0.07
     Zh
    -0.07
     grátis
    -0.06
    StackSize
    -0.06
     To
    -0.06
     palm
    -0.06
    Loads
    -0.06
    Ot
    -0.06
     kad
    -0.06
     implic
    -0.06
    POSITIVE LOGITS
     melanch
    0.06
    sil
    0.06
     PRI
    0.06
    /Documents
    0.06
    ulent
    0.06
    admin
    0.06
     начинает
    0.06
    inded
    0.06
    ersive
    0.05
     ED
    0.05
    Act Density 0.011%

    No Known Activations