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
    (lower
    -0.07
    кости
    -0.07
    Neither
    -0.06
    .Process
    -0.06
    otlin
    -0.06
    _ALT
    -0.06
     "-
    -0.06
    place
    -0.06
    Mas
    -0.06
    .closed
    -0.06
    POSITIVE LOGITS
    ]}↵
    0.06
    iane
    0.06
     Dating
    0.06
     advertisements
    0.06
    _MATH
    0.06
     Mourinho
    0.06
    :'.$
    0.06
    >');↵↵
    0.06
     Diagnostic
    0.06
    (())↵
    0.06
    Act Density 0.291%

    No Known Activations