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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valves
    -0.06
    роничес
    -0.06
    trail
    -0.06
     Deprecated
    -0.06
     */;↵
    -0.05
     Reflection
    -0.05
    έργ
    -0.05
     chaining
    -0.05
     Lone
    -0.05
    χία
    -0.05
    POSITIVE LOGITS
     şiş
    0.07
    operate
    0.06
     annihil
    0.06
     workaround
    0.06
     xxx
    0.06
    (yy
    0.06
     turist
    0.06
     td
    0.06
     firebase
    0.06
    _bundle
    0.06
    Act Density 0.000%

    No Known Activations