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
     made
    -0.07
     chu
    -0.06
    Actual
    -0.06
    ("@
    -0.06
    -art
    -0.06
     ignored
    -0.06
     manageable
    -0.06
     shows
    -0.06
    hus
    -0.06
    Environment
    -0.06
    POSITIVE LOGITS
     humanoid
    0.06
     cường
    0.06
    	Address
    0.06
    	fprintf
    0.06
    �
    0.06
     вуз
    0.06
     �
    0.06
    (att
    0.06
     SimpleName
    0.06
     commend
    0.06
    Act Density 0.113%

    No Known Activations