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
    �
    -0.06
     ベ
    -0.06
    YN
    -0.06
    EEP
    -0.06
    ==="
    -0.06
    .z
    -0.06
     SPL
    -0.06
     ulong
    -0.06
    notated
    -0.06
    ErrMsg
    -0.06
    POSITIVE LOGITS
     exit
    0.07
     elemental
    0.07
    ).[
    0.07
    难
    0.07
    .Euler
    0.07
    ropy
    0.06
    Leaf
    0.06
     combat
    0.06
     creator
    0.06
     underrated
    0.06
    Act Density 0.212%

    No Known Activations