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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fetch
    -0.07
     '~/
    -0.07
    =$
    -0.06
    }");
↵
    -0.06
     Compute
    -0.06
    	next
    -0.06
     Augusta
    -0.06
     ALIGN
    -0.06
    ("")↵
    -0.06
     COMPUT
    -0.06
    POSITIVE LOGITS
    Une
    0.07
    paste
    0.06
     пре
    0.06
    �
    0.06
    uckles
    0.06
     weaker
    0.06
     Rodrig
    0.06
     назнач
    0.06
    SEM
    0.06
    ém
    0.06
    Act Density 0.000%

    No Known Activations