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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     individuals
    -0.07
     unter
    -0.07
     Manga
    -0.06
     persecution
    -0.06
    aska
    -0.06
    _MAJOR
    -0.06
     Remarks
    -0.06
    κ
    -0.06
    δυ
    -0.06
     دنیا
    -0.06
    POSITIVE LOGITS
     closets
    0.08
    @Column
    0.07
     First
    0.07
    ,arg
    0.06
     FUCK
    0.06
    _EDGE
    0.06
     NAME
    0.06
     rest
    0.06
    _CLEAR
    0.06
    危
    0.06
    Act Density 0.032%

    No Known Activations