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

    Neuronpedia

    INDEX
    Explanations

    li

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    744
    -0.07
     دل
    -0.06
     disables
    -0.06
     být
    -0.06
    _aliases
    -0.06
    올
    -0.06
    微笑
    -0.06
     flank
    -0.06
     ease
    -0.06
     กล
    -0.06
    POSITIVE LOGITS
    ."↵↵
    0.08
    ?"↵↵
    0.07
     esa
    0.07
     Scho
    0.07
     Integr
    0.07
    ect
    0.06
     pressed
    0.06
    CBC
    0.06
     Pron
    0.06
    (canvas
    0.06
    Act Density 0.006%

    No Known Activations