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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Turnbull
    -0.06
    _tw
    -0.06
    ifty
    -0.06
    .Comm
    -0.06
    urpose
    -0.06
     bold
    -0.06
    375
    -0.06
     Aub
    -0.06
    anuts
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
    deserialize
    0.07
    せて
    0.07
    criteria
    0.06
    (S
    0.06
    SECTION
    0.06
    اشة
    0.06
     callbacks
    0.06
     discrimin
    0.06
    ,n
    0.06
    <body
    0.06
    Act Density 0.000%

    No Known Activations