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

    Neuronpedia

    INDEX
    Explanations

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nobel
    -0.07
     Moss
    -0.07
    	url
    -0.06
    .Template
    -0.06
    ATO
    -0.06
    Allen
    -0.06
    RequestBody
    -0.06
    (File
    -0.06
    руш
    -0.06
    _arr
    -0.06
    POSITIVE LOGITS
     onde
    0.07
    ively
    0.07
     claro
    0.06
    .loaded
    0.06
    __),
    0.06
     혹
    0.06
     болезни
    0.06
     потом
    0.06
     barren
    0.06
     лег
    0.06
    Act Density 0.018%

    No Known Activations