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

    Neuronpedia

    INDEX
    Explanations

    fusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bart
    -0.07
    173
    -0.07
    Deprecated
    -0.07
    _week
    -0.07
     cray
    -0.07
     crank
    -0.07
    (sql
    -0.07
    Rad
    -0.06
     cort
    -0.06
     Samar
    -0.06
    POSITIVE LOGITS
     Fusion
    0.12
     fusion
    0.10
    usz
    0.09
     fused
    0.08
    usion
    0.08
     fuse
    0.07
    уск
    0.07
     Union
    0.07
    uces
    0.07
    uns
    0.07
    Act Density 0.005%

    No Known Activations