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

    Neuronpedia

    INDEX
    Explanations

    param

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     долл
    -0.07
    .rc
    -0.07
    �
    -0.07
    ʟ
    -0.07
    אזרח
    -0.07
    _letters
    -0.06
    쿅
    -0.06
    .Compiler
    -0.06
     outdoors
    -0.06
    ست
    -0.06
    POSITIVE LOGITS
     responses
    0.07
    +'
    0.07
    …"
    0.07
    Spy
    0.07
    Corn
    0.07
    rpc
    0.06
    amous
    0.06
    を持つ
    0.06
     Deferred
    0.06
     Savage
    0.06
    Act Density 0.000%

    No Known Activations