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

    Neuronpedia

    INDEX
    Explanations

    Geography

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     councils
    -0.07
    nov
    -0.06
    Drv
    -0.06
    Hover
    -0.06
    NG
    -0.06
     nf
    -0.06
    ेल
    -0.06
     expressly
    -0.06
     oficial
    -0.06
    oy
    -0.06
    POSITIVE LOGITS
    -facing
    0.07
     Pu
    0.06
     manifest
    0.06
    enis
    0.06
     scav
    0.06
    /../
    0.06
    erde
    0.06
     Paras
    0.06
    ){}↵
    0.06
     deliberate
    0.06
    Act Density 0.007%

    No Known Activations