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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lage
    -0.07
    odzi
    -0.07
    节点
    -0.07
    илання
    -0.07
     즉
    -0.07
    modulo
    -0.07
    .Interfaces
    -0.07
    国产
    -0.06
    .nativeElement
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    (~
    0.07
     constitution
    0.07
     dreams
    0.07
     writing
    0.07
     requirements
    0.07
     consolidate
    0.07
     person
    0.07
     grades
    0.06
     dealt
    0.06
    nis
    0.06
    Act Density 0.026%

    No Known Activations