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

    Neuronpedia

    INDEX
    Explanations

    location prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hundred
    -0.06
    الح
    -0.06
    EditText
    -0.06
     Rusya
    -0.06
    -0.06
    と
    -0.06
    Peace
    -0.06
    џџџџ
    -0.06
    ();↵↵↵↵
    -0.06
     }↵↵↵↵↵↵
    -0.06
    POSITIVE LOGITS
    VER
    0.07
    parate
    0.07
    сед
    0.07
     vriend
    0.07
     ancestry
    0.06
     towering
    0.06
     contracting
    0.06
    า�
    0.06
     getVersion
    0.06
    ver
    0.06
    Act Density 0.018%

    No Known Activations