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

    Neuronpedia

    INDEX
    Explanations

    Yad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رد
    -0.07
    加
    -0.07
    .$$
    -0.07
    handles
    -0.07
     požad
    -0.06
    ící
    -0.06
    ti
    -0.06
     I
    -0.06
    کی
    -0.06
     U
    -0.06
    POSITIVE LOGITS
    örper
    0.07
    /ec
    0.07
     rum
    0.06
     prompting
    0.06
     Ach
    0.06
     Yad
    0.06
     DECL
    0.06
     бел
    0.06
    ?><?
    0.06
    (part
    0.06
    Act Density 0.022%

    No Known Activations