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

    Neuronpedia

    INDEX
    Explanations

    square

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quoted
    -0.06
    _dw
    -0.06
     t
    -0.06
     zab
    -0.06
     rog
    -0.06
    _exception
    -0.06
    _POINTER
    -0.06
    adata
    -0.06
     ev
    -0.06
     scars
    -0.06
    POSITIVE LOGITS
     Slice
    0.06
     Nazi
    0.06
    �
    0.06
     Fulton
    0.06
    .AddItem
    0.06
    Sup
    0.06
     },
↵
    0.06
    重大
    0.06
    )?;↵
    0.06
    -Christian
    0.06
    Act Density 0.001%

    No Known Activations