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

    Neuronpedia

    INDEX
    Explanations

    .mod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     приня
    -0.08
                                 ↵
    -0.07
     �
    -0.07
     กร
    -0.06
    ;}
↵
    -0.06
     içeren
    -0.06
    }$/
    -0.06
    !<
    -0.06
                                  ↵
    -0.06
    ümüz
    -0.06
    POSITIVE LOGITS
    country
    0.07
    rypto
    0.07
    心里
    0.07
    TODO
    0.06
    charger
    0.06
     lodge
    0.06
    ichtet
    0.06
     honoring
    0.06
     Ravens
    0.06
    .Measure
    0.06
    Act Density 0.000%

    No Known Activations