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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...
    -0.08
    갊
    -0.07
    total
    -0.07
    ethereum
    -0.07
     pedig
    -0.07
    سكان
    -0.07
    Terminate
    -0.07
    fan
    -0.07
    ruptcy
    -0.07
     hunted
    -0.06
    POSITIVE LOGITS
     �
    0.08
    	inter
    0.08
    Ẳ
    0.07
     collaborative
    0.07
    �
    0.07
     Рус
    0.07
    另有
    0.07
    lers
    0.07
    atisation
    0.07
     HEALTH
    0.07
    Act Density 1.300%

    No Known Activations