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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pent
    -0.07
     fellowship
    -0.06
     Tento
    -0.06
    $username
    -0.06
     gleich
    -0.06
     ordinances
    -0.06
    Programming
    -0.06
     margin
    -0.06
    ศาสตร
    -0.06
    abella
    -0.06
    POSITIVE LOGITS
     всіх
    0.07
    .hxx
    0.07
    _PW
    0.07
    ']↵↵↵
    0.06
     TREE
    0.06
     dikke
    0.06
     }
↵
↵
↵
    0.06
    .BOLD
    0.06
    ];↵
    0.06
    _TIMER
    0.06
    Act Density 0.154%

    No Known Activations