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

    Neuronpedia

    INDEX
    Explanations

    code variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    statistical
    0.37
     Burgh
    0.37
    ο
    0.37
     socalled
    0.35
    ❘
    0.35
     celebrating
    0.34
    Environmental
    0.34
    Sanchez
    0.34
     olyan
    0.34
    environmental
    0.34
    POSITIVE LOGITS
    _
    0.66
    \_
    0.47
    +
    0.45
    -
    0.38
     latéraux
    0.38
    ="
    0.36
     +=
    0.35
     params
    0.34
    +$
    0.34
     +
    0.34
    Act Density 0.038%

    No Known Activations