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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    checkbox
    -0.06
     століття
    -0.06
    )frame
    -0.06
     Civ
    -0.06
    akhir
    -0.06
    ,i
    -0.06
     campos
    -0.06
    )>=
    -0.06
    venient
    -0.06
     cx
    -0.06
    POSITIVE LOGITS
     طبي
    0.07
     둘
    0.07
    Course
    0.07
    乳
    0.06
    NES
    0.06
    ART
    0.06
     beast
    0.06
     serve
    0.06
    (high
    0.06
     mono
    0.06
    Act Density 0.000%

    No Known Activations