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

    Neuronpedia

    INDEX
    Explanations

    Explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barber
    -0.07
     podemos
    -0.07
     '_'
    -0.07
    Titulo
    -0.07
     decision
    -0.07
    employer
    -0.07
     dissent
    -0.06
    ivated
    -0.06
     overt
    -0.06
     pimp
    -0.06
    POSITIVE LOGITS
     SPF
    0.07
    俄乌
    0.07
     размещен
    0.07
     copp
    0.07
     �
    0.06
    ╋
    0.06
    �
    0.06
    _membership
    0.06
    퀄
    0.06
    schlie
    0.06
    Act Density 0.182%

    No Known Activations