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

    Neuronpedia

    INDEX
    Explanations

    Engine size/type

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Destroy
    -0.08
     brands
    -0.07
     moment
    -0.06
     supermarket
    -0.06
    سه
    -0.06
     reordered
    -0.06
     aids
    -0.06
     deny
    -0.06
    _rename
    -0.06
    Java
    -0.06
    POSITIVE LOGITS
     zkou
    0.08
     Morav
    0.07
     metam
    0.06
    운
    0.06
     HeaderComponent
    0.06
     Shooter
    0.06
    ling
    0.06
     víde
    0.06
    Balance
    0.06
     namoro
    0.06
    Act Density 0.008%

    No Known Activations