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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Help
    -0.07
     tid
    -0.07
    www
    -0.07
     annotate
    -0.07
     pathways
    -0.06
     traveled
    -0.06
    死
    -0.06
    LANGUAGE
    -0.06
     homosex
    -0.06
     devastated
    -0.06
    POSITIVE LOGITS
    504
    0.07
    apeake
    0.07
     Teresa
    0.06
    _putstr
    0.06
    shader
    0.06
     malloc
    0.06
    .bottomAnchor
    0.06
    	glm
    0.06
    ROUT
    0.06
    rát
    0.06
    Act Density 0.131%

    No Known Activations