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

    Neuronpedia

    INDEX
    Explanations

    ham

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unch
    -0.08
     delic
    -0.07
    สภาพ
    -0.07
    덬
    -0.07
     gaz
    -0.07
     hotspot
    -0.07
    ROP
    -0.07
    ﱏ
    -0.07
    oop
    -0.07
    Allows
    -0.07
    POSITIVE LOGITS
     이루
    0.08
    骘
    0.08
    交织
    0.08
    0.08
     Может
    0.08
     incremented
    0.08
    书记
    0.07
    (horizontal
    0.07
     Thirty
    0.07
    ational
    0.07
    Act Density 0.008%

    No Known Activations