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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guerr
    -0.07
    	Http
    -0.07
     arou
    -0.07
    <Path
    -0.07
    orage
    -0.06
    >Nama
    -0.06
     incom
    -0.06
     krij
    -0.06
    .Designer
    -0.06
    (ds
    -0.06
    POSITIVE LOGITS
    angement
    0.07
    anches
    0.07
     revamped
    0.06
    neau
    0.06
    映画
    0.06
     Discount
    0.06
     migrations
    0.06
     literally
    0.06
     منطقه
    0.06
    월
    0.06
    Act Density 0.003%

    No Known Activations