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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realizes
    -0.06
     understand
    -0.06
     postponed
    -0.06
    -ph
    -0.06
     understands
    -0.06
    	strcpy
    -0.06
     UPDATED
    -0.06
     Too
    -0.06
     konusunda
    -0.06
    ragen
    -0.06
    POSITIVE LOGITS
     захворю
    0.07
     구글
    0.07
     �
    0.07
     totiž
    0.06
     yola
    0.06
    .Secret
    0.06
    _fix
    0.06
     botanical
    0.06
     trafficking
    0.06
    ){
↵
↵
    0.06
    Act Density 0.005%

    No Known Activations