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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Have
    -0.06
    .World
    -0.06
     ด
    -0.06
     flap
    -0.06
     affid
    -0.06
     ویرایش
    -0.06
    ibu
    -0.06
    _FACTORY
    -0.05
     Barang
    -0.05
    _dispatch
    -0.05
    POSITIVE LOGITS
    clc
    0.07
    itled
    0.07
     retirees
    0.07
     reduction
    0.07
     Nie
    0.07
     NSStringFromClass
    0.07
    Credentials
    0.06
    .onDestroy
    0.06
     disconnected
    0.06
    ře
    0.06
    Act Density 0.000%

    No Known Activations