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

    Neuronpedia

    INDEX
    Explanations

    intervene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     POP
    -0.06
     enjoys
    -0.06
     деле
    -0.06
    iado
    -0.06
     POR
    -0.06
    _parts
    -0.06
     brag
    -0.06
     lod
    -0.05
    'hui
    -0.05
     Mö
    -0.05
    POSITIVE LOGITS
     intervening
    0.08
     subsequent
    0.07
     xmlhttp
    0.07
     _:
    0.07
     intervened
    0.07
     anál
    0.07
    itored
    0.07
     gerekir
    0.07
     Neptune
    0.07
    Ин
    0.07
    Act Density 0.006%

    No Known Activations