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

    Neuronpedia

    INDEX
    Explanations

    Money and transactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metal
    -0.08
     wave
    -0.07
    uses
    -0.07
    Exit
    -0.07
    صد
    -0.07
    idak
    -0.07
     Causes
    -0.07
    argo
    -0.06
     Retrofit
    -0.06
    (saved
    -0.06
    POSITIVE LOGITS
     veri
    0.07
     grassroots
    0.07
     Tribal
    0.06
    мотря
    0.06
    inputEmail
    0.06
    (vertices
    0.06
    [maxn
    0.06
     गय
    0.06
     tout
    0.06
     контр
    0.06
    Act Density 0.106%

    No Known Activations