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

    Neuronpedia

    INDEX
    Explanations

    medical concerns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    f
    -0.07
    .delete
    -0.07
     NV
    -0.06
     gossip
    -0.06
     interrupted
    -0.06
    -sponsored
    -0.06
     Unary
    -0.06
    _dependency
    -0.06
    	fun
    -0.06
    estre
    -0.06
    POSITIVE LOGITS
    �
    0.06
     Bloody
    0.06
     prů
    0.06
    zenia
    0.06
     минут
    0.06
    -dess
    0.06
     الل
    0.06
     DAG
    0.06
    χεδόν
    0.06
     planta
    0.06
    Act Density 0.034%

    No Known Activations