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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    랑
    -0.06
    /calendar
    -0.06
    	A
    -0.06
     Pulse
    -0.06
    476
    -0.06
    ану
    -0.06
    243
    -0.06
     mostrar
    -0.06
    sharing
    -0.06
    :Is
    -0.06
    POSITIVE LOGITS
     dirt
    0.07
     urge
    0.07
    compound
    0.07
     dang
    0.07
     inconsistencies
    0.07
     �
    0.06
    mary
    0.06
    Hits
    0.06
    ARY
    0.06
     encouraging
    0.06
    Act Density 0.032%

    No Known Activations