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

    Neuronpedia

    INDEX
    Explanations

    return value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jahteraan
    0.43
     달려
    0.43
     принадлежа
    0.42
    utung
    0.38
    라이언트
    0.38
     घंटे
    0.38
     concurring
    0.37
    Wales
    0.37
    لاك
    0.37
     aparición
    0.37
    POSITIVE LOGITS
    ees
    0.57
    value
    0.55
     returnValue
    0.55
     value
    0.48
     Return
    0.46
    값을
    0.46
     लौटने
    0.46
     nilai
    0.45
     zwr
    0.45
    返す
    0.44
    Act Density 0.024%

    No Known Activations