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

    Neuronpedia

    INDEX
    Explanations

    Arb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transf
    -0.06
     appointments
    -0.06
    Insert
    -0.06
     tmp
    -0.06
    >y
    -0.06
    Alloc
    -0.06
     Máy
    -0.06
    >V
    -0.06
    getPath
    -0.06
    phoneNumber
    -0.06
    POSITIVE LOGITS
     Гар
    0.07
     Accessories
    0.06
     Family
    0.06
    .Scale
    0.06
     resets
    0.06
    �
    0.06
     tảng
    0.06
     endeavor
    0.06
     Island
    0.06
    bo
    0.06
    Act Density 0.014%

    No Known Activations