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

    Neuronpedia

    INDEX
    Explanations

    Recipe and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τύ
    -0.08
    enarios
    -0.08
    dod
    -0.07
    över
    -0.07
     Transmission
    -0.07
    know
    -0.07
     Entertainment
    -0.07
     transmission
    -0.07
    retr
    -0.07
    _MESSAGE
    -0.07
    POSITIVE LOGITS
    (Duration
    0.08
     движения
    0.08
     сосед
    0.08
     проп
    0.08
    (Default
    0.07
     член
    0.07
    aman
    0.07
     enkele
    0.07
     шах
    0.07
    ?..
    0.07
    Act Density 0.001%

    No Known Activations